© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3151
    Prev
    Next
    INDEX
    Explanations

    the word "take" and past/present tense of it.

    oai_token-act-pair · gemini-2.0-flash

    multiple general contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     SEDS
    -0.70
    bootstrapcdn
    -0.68
    WriteAttribute
    -0.67
    rrggbb
    -0.66
    TintMode
    -0.59
    Legături
    -0.59
     متحده
    -0.58
     NSCoder
    -0.57
    Into
    -0.57
    dotenv
    -0.56
    POSITIVE LOGITS
     on
    0.63
    LEADING
    0.50
    ✨:
    0.48
     Indira
    0.48
    on
    0.47
     lais
    0.46
     FileWriter
    0.44
    #+#
    0.43
     SQLException
    0.43
    manes
    0.43
    Activations Density 0.263%

    No Known Activations