© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6522
    Prev
    Next
    INDEX
    Explanations

    words ending with "ci", "logist", "tici", "tom", "graphy", or "etic"

    oai_token-act-pair · gemini-2.0-flash

    words related to licensing and parameters

    np_token-act-pair-logits · gpt-4o-mini

    say "z" words

    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
     Meksiku
    -0.94
    verwijspagina
    -0.94
    MigrationBuilder
    -0.93
    ftagPool
    -0.91
    IsPostBack
    -0.90
     समीक्षक
    -0.88
    RenderAtEndOf
    -0.87
    +#+#
    -0.85
     resourceCulture
    -0.82
    OGND
    -0.80
    POSITIVE LOGITS
    stan
    0.45
    ss
    0.45
    ck
    0.43
    st
    0.42
     F
    0.41
    盡
    0.41
    om
    0.40
    overrightarrow
    0.40
    de
    0.39
    zen
    0.39
    Activations Density 1.383%

    No Known Activations