© 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. 9240
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to being in agreement

    oai_token-act-pair · gemini-2.0-flash

    agreement and acceptance

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

    agree

    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
     հղումներ
    -0.59
    Przypisy
    -0.59
     agree
    -0.58
     Cargo
    -0.56
    ={({
    -0.55
     agreed
    -0.54
    oO
    -0.54
    -',
    -0.53
     configur
    -0.52
    agreed
    -0.52
    POSITIVE LOGITS
    ArgsConstructor
    0.60
     EconPapers
    0.58
     with
    0.55
     propOrder
    0.53
     defaultstate
    0.53
     to
    0.53
     without
    0.51
    providedIn
    0.49
    NavController
    0.49
     that
    0.46
    Activations Density 3.964%

    No Known Activations