© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14178
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking terms in recipes

    oai_token-act-pair · gemini-2.0-flash

    alcoholic recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    featureID
    -0.84
    <bos>
    -0.67
     disambiguazione
    -0.62
     mergeFrom
    -0.54
    +#+
    -0.54
    contentLoaded
    -0.53
     Infórmanos
    -0.52
    ::_('
    -0.51
    DIPSETTING
    -0.51
    archiviato
    -0.50
    POSITIVE LOGITS
     jsPsych
    0.64
     initComponents
    0.58
    الإنجليزية
    0.52
    cluye
    0.52
    AndEndTag
    0.47
    Struct
    0.45
     GenerationType
    0.45
     unrelated
    0.44
    nsyn
    0.44
    ofire
    0.44
    Activations Density 0.229%

    No Known Activations