© 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. 9265
    Prev
    Next
    INDEX
    Explanations

    lines containing substrings like "http", "com", "github", and "@"

    oai_token-act-pair · gemini-2.0-flash

    Period token

    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
    <bos>
    -0.71
    S
    -0.66
    '
    -0.59
    D
    -0.58
    T
    -0.56
    N
    -0.53
    :");
    -0.51
    !")
    -0.50
     ''
    -0.49
    M
    -0.48
    POSITIVE LOGITS
     Audiodateien
    0.76
     تانيه
    0.73
    SourceChecksum
    0.66
    ResumeLayout
    0.66
     FetchType
    0.64
    gonz
    0.63
    المناصب
    0.62
    mybatisplus
    0.61
    uxxxx
    0.61
    usercontent
    0.60
    Activations Density 15.690%

    No Known Activations