© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12437
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or disagreement, and code snippets

    oai_token-act-pair · gemini-2.0-flash

    pas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    bootstrapcdn
    -0.90
    findpost
    -0.87
     disambiguazione
    -0.84
    principalTable
    -0.82
     transfieras
    -0.77
    PropertyChanging
    -0.76
    NavController
    -0.76
     Référence
    -0.76
     للاسماء
    -0.75
    labus
    -0.73
    POSITIVE LOGITS
    <bos>
    0.53
     fullt
    0.48
    gså
    0.46
    (--
    0.42
     sevi
    0.42
     zicht
    0.41
    νονται
    0.41
    ureusement
    0.41
    vice
    0.40
    OrEqual
    0.40
    Activations Density 1.754%

    No Known Activations