© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13129
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical equations and expressions

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AndEndTag
    -0.69
     estekak
    -0.66
    ArgsConstructor
    -0.58
    LookAnd
    -0.55
    ]-->
    -0.55
    BagConstraints
    -0.55
     typelib
    -0.54
     disambiguazione
    -0.53
    MigrationBuilder
    -0.51
    XmlAccessType
    -0.50
    POSITIVE LOGITS
    ITUDE
    0.61
    ULAS
    0.56
    ially
    0.55
    ุน
    0.54
    ńcu
    0.54
     AudioClip
    0.54
     extr
    0.53
    LYN
    0.52
     كومونز
    0.52
    icose
    0.52
    Activations Density 2.916%

    No Known Activations