© 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. 7852
    Prev
    Next
    INDEX
    Explanations

    statements of fact, indicated by the word "is", "are", or "was".

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating information disclosure

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

    describing

    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
     mód
    -0.50
    databind
    -0.46
    iuo
    -0.44
    állítás
    -0.43
    onomian
    -0.42
    VersionUID
    -0.40
     kiệm
    -0.40
    TProtocol
    -0.40
    Passing
    -0.39
    createComponent
    -0.39
    POSITIVE LOGITS
     mentioned
    1.45
     described
    1.42
     stated
    1.40
     indicated
    1.34
     shown
    1.30
     explained
    1.23
     Mentioned
    1.23
     listed
    1.20
     revealed
    1.17
     specified
    1.16
    Activations Density 2.971%

    No Known Activations