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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14810
    Prev
    Next
    INDEX
    Explanations

    words used in code and programming, including comments, code snippets, and related terms

    oai_token-act-pair · gemini-2.0-flash

    code and foreign languages

    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
     of
    -1.40
    of
    -1.36
     de
    -1.23
     OF
    -1.18
     Of
    -1.07
    OF
    -1.05
    Of
    -1.05
     di
    -1.01
     DE
    -0.85
     De
    -0.83
    POSITIVE LOGITS
     mer
    0.50
    +#+#
    0.46
    dav
    0.44
    Бележки
    0.43
    ablon
    0.41
    vertido
    0.40
    bals
    0.40
    moid
    0.39
    alan
    0.39
     adatok
    0.38
    Activations Density 0.989%

    No Known Activations