© 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. 3912
    Prev
    Next
    INDEX
    Explanations

    instances where something is being described, or something is being favorably reviewed

    oai_token-act-pair · gemini-2.0-flash

    is/are

    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
    esModule
    -0.62
     snippetHide
    -0.59
    __*/
    -0.57
     समीक्षाएं
    -0.55
    دانشنامهٔ
    -0.52
     onResponse
    -0.49
    ंदीखरीदारी
    -0.47
    /',
    -0.47
    ."));
    -0.47
     AspNetCore
    -0.47
    POSITIVE LOGITS
    SPATH
    0.61
     about
    0.59
     impeccable
    0.59
    AppMethodBeat
    0.57
    Inflater
    0.57
     relaxed
    0.56
    appé
    0.56
     top
    0.56
    DataSetChanged
    0.55
     fruitful
    0.53
    Activations Density 1.599%

    No Known Activations