© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7310
    Prev
    Next
    INDEX
    Explanations

    language related to quantitative measures, like size, electric current, or degrees.

    oai_token-act-pair · gemini-2.0-flash

    units of measure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     GenerationType
    -1.05
    adaptiveStyles
    -0.91
    $_['
    -0.86
    TemporalType
    -0.86
     Signalez
    -0.86
     gynhyrchwyd
    -0.85
     utafitiHapana
    -0.85
    yntaxException
    -0.85
     autorytatywna
    -0.84
     calendriers
    -0.83
    POSITIVE LOGITS
    .
    0.50
    spół
    0.49
     or
    0.46
    ,
    0.44
     and
    0.43
    fastjson
    0.41
     max
    0.41
     (
    0.38
     femininos
    0.38
    ówki
    0.37
    Activations Density 18.354%

    No Known Activations