© 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-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261216
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    1.18
    ید
    1.16
    য়া
    1.16
    した
    1.07
    ست
    1.04
    し
    1.04
    ת
    1.00
    ۲
    0.98
    iy
    0.96
    ati
    0.90
    POSITIVE LOGITS
    s
    1.46
    z
    1.12
    k
    1.11
     In
    1.02
    f
    0.99
    y
    0.99
    the
    0.98
    in
    0.95
    이었
    0.91
    have
    0.89
    Activations Density 0.000%

    No Known Activations