© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11458
    Prev
    Next
    INDEX
    Explanations

    modals, past tense verb forms, and words or phrases that express approximation or tentativeness

    oai_token-act-pair · gemini-2.0-flash

    say "as"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AS
    -0.84
    цезда
    -0.69
     disambiguazione
    -0.67
     Audiodateien
    -0.64
    ASU
    -0.60
    <bos>
    -0.59
    цездатний
    -0.55
    Према
    -0.53
    niająca
    -0.53
     كومونز
    -0.51
    POSITIVE LOGITS
     as
    2.03
     sebagai
    1.41
     как
    1.20
     jako
    1.08
     як
    1.04
     como
    0.97
    作为
    0.91
     као
    0.91
     kao
    0.90
     comme
    0.88
    Activations Density 1.309%

    No Known Activations