© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11467
    Prev
    Next
    INDEX
    Explanations

    what appears to be partial or abbreviated words

    oai_token-act-pair · gemini-2.0-flash

    random text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    a
    -2.61
    aah
    -1.02
    aed
    -0.94
    aia
    -0.94
    aA
    -0.91
    ahi
    -0.90
    aing
    -0.90
    aR
    -0.90
    aas
    -0.86
    ا
    -0.84
    POSITIVE LOGITS
    ostante
    0.68
    вної
    0.44
    ълга
    0.44
    CDATA
    0.43
    Cuánt
    0.43
     isang
    0.42
    querySelector
    0.41
    tioners
    0.41
    dce
    0.40
     sebuah
    0.40
    Activations Density 3.468%

    No Known Activations