© 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. 261209
    Prev
    Next
    INDEX
    Explanations

    pwnagotchi or pwned

    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
    '
    1.52
    на
    1.17
    在
    1.17
    ก
    1.16
    ৬
    0.98
    知道
    0.98
     التي
    0.96
    '}$
    0.95
    ק
    0.95
     erwähnt
    0.95
    POSITIVE LOGITS
    it
    1.83
    ut
    1.40
    hi
    1.23
    in
    1.22
    u
    1.22
    ro
    1.18
    hrs
    1.17
    یس
    1.16
    is
    1.14
    as
    1.14
    Activations Density 0.000%

    No Known Activations