© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9026
    Prev
    Next
    INDEX
    Explanations

    words or phrases about data analysis, technical or scientific writing, legal terms, and recreational trails.

    oai_token-act-pair · gemini-2.0-flash

    phrases related to data processing and comparison

    np_token-act-pair-logits · gpt-4o-mini

    academic writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يكب
    -1.06
    #+#
    -1.01
     nakalista
    -1.00
    ConstraintMaker
    -0.99
     itſelf
    -0.97
    RenderAtEndOf
    -0.91
    ''');
    -0.91
    migrationBuilder
    -0.88
    neſs
    -0.88
    ſelf
    -0.87
    POSITIVE LOGITS
     of
    0.69
    .
    0.59
     mattino
    0.59
     célèbres
    0.55
     suivie
    0.52
     soñar
    0.49
    ,
    0.49
     pomeriggio
    0.48
     decidió
    0.47
     colère
    0.46
    Activations Density 21.450%

    No Known Activations