© 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. 8637
    Prev
    Next
    INDEX
    Explanations

    character sequences and stems that are parts of words.

    oai_token-act-pair · gemini-2.0-flash

    Text snippets

    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
    ian
    -0.40
    ini
    -0.39
    ial
    -0.39
    attaque
    -0.39
    ly
    -0.39
    is
    -0.38
    ัน
    -0.38
    in
    -0.38
    يا
    -0.38
    its
    -0.38
    POSITIVE LOGITS
    ech
    0.81
    eler
    0.78
    ej
    0.76
    epro
    0.76
    eb
    0.75
    e
    0.75
    ele
    0.75
    etype
    0.75
    ep
    0.73
    eche
    0.73
    Activations Density 6.524%

    No Known Activations