© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 756
    Prev
    Next
    INDEX
    Explanations

    the phrase "at the very"

    oai_token-act-pair · gemini-2.0-flash

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     mon
    -0.46
    ειτουργ
    -0.42
     modern
    -0.42
    osis
    -0.42
    leriyle
    -0.41
     with
    -0.40
    ndag
    -0.39
     sàng
    -0.39
    而已
    -0.39
    corde
    -0.38
    POSITIVE LOGITS
    tvguidetime
    0.84
     createSlice
    0.80
    ArgsConstructor
    0.75
     disambiguazione
    0.74
    sizeCache
    0.71
    esModule
    0.69
    makeText
    0.69
    ValueGenerated
    0.68
    endsection
    0.68
     [?]
    0.67
    Activations Density 0.769%

    No Known Activations