© 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. 261273
    Prev
    Next
    INDEX
    Explanations

    proof of theorem

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    )
    1.68
    -
    1.63
    ↵↵
    1.31
    )$
    1.24
    a
    1.22
    am
    1.19
    =
    1.19
    ี
    1.17
    :
    1.16
    >
    1.09
    POSITIVE LOGITS
     في
    1.22
     in
    1.07
    ق
    1.02
    h
    0.96
     в
    0.93
    óticos
    0.92
    ш
    0.91
     कीमत
    0.89
    在
    0.89
    ﯼ
    0.88
    Activations Density 0.010%

    No Known Activations