© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16085
    Prev
    Next
    INDEX
    Explanations

    a wide range of topics spanning from family and relationships to food, entertainment, social issues, and science.

    oai_token-act-pair · gemini-2.0-flash

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Personendaten
    -1.06
    LookAnd
    -0.75
    done
    -0.74
     виправивши
    -0.73
    Datuak
    -0.72
     done
    -0.72
    TemporalType
    -0.70
     дописавши
    -0.68
     unknownFields
    -0.68
    Tembelea
    -0.68
    POSITIVE LOGITS
    quia
    0.46
     Stra
    0.43
    matically
    0.42
    Str
    0.41
    mtp
    0.40
    rups
    0.40
     str
    0.40
     Âu
    0.39
     Gil
    0.39
     STR
    0.38
    Activations Density 35.718%

    No Known Activations