© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14647
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, possessive pronouns, and words relating to personal relationships and feelings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     CreateTagHelper
    -0.71
     createState
    -0.62
    eleste
    -0.58
    rrggbb
    -0.56
    تقاوى
    -0.55
    abag
    -0.53
    __))
    -0.53
    帖最后由
    -0.53
    tomans
    -0.51
    indexPath
    -0.51
    POSITIVE LOGITS
    HideFlags
    0.57
     interchangeable
    0.53
    PreferredItem
    0.50
     Queste
    0.50
    արի
    0.47
    Precalculus
    0.47
    fiore
    0.46
     Muskel
    0.46
     transfieras
    0.46
     funktioner
    0.46
    Activations Density 14.308%

    No Known Activations