© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7510
    Prev
    Next
    INDEX
    Explanations

    terms related to family and relationships

    oai_token-act-pair · gemini-2.0-flash

    families

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    WireFormatLite
    -0.81
     Савезне
    -0.80
    VersionUID
    -0.62
     \%)
    -0.61
    migrationBuilder
    -0.61
    CrossOrigin
    -0.60
    databind
    -0.60
    UnknownFields
    -0.56
    jooq
    -0.56
     remb
    -0.56
    POSITIVE LOGITS
    קישורים
    0.46
     late
    0.46
    ########.
    0.44
     Late
    0.44
    Skocz
    0.43
    nestjs
    0.42
    วก
    0.42
     One
    0.41
     Dodson
    0.41
     Suomessa
    0.40
    Activations Density 1.928%

    No Known Activations