© 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. 4372
    Prev
    Next
    INDEX
    Explanations

    responses or statements of agreement or disagreement, especially "yes" and "no", as well as questions and answers.

    oai_token-act-pair · gemini-2.0-flash

    programming terms or code snippets

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

    yes and no answers

    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
     definitely
    -0.63
    Yes
    -0.63
     Yes
    -0.62
     certainly
    -0.61
    Sí
    -0.60
     surely
    -0.59
     sure
    -0.57
    Certainly
    -0.56
     yes
    -0.56
    Sure
    -0.56
    POSITIVE LOGITS
    enumii
    0.64
    Espèce
    0.56
    enumi
    0.56
    ViewInit
    0.52
    ējās
    0.49
    fromnode
    0.49
    ResumeLayout
    0.48
    OGND
    0.47
    istió
    0.47
    appcompat
    0.47
    Activations Density 1.259%

    No Known Activations