© 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. 261289
    Prev
    Next
    INDEX
    Explanations

    Quark, Kven, kväll

    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
    2
    1.55
    6
    1.28
    ()
    1.20
    \
    1.20
    5
    1.16
    1
    1.15
    9
    1.15
    8
    1.14
    (
    1.13
    c
    1.08
    POSITIVE LOGITS
    া
    1.07
    ۰
    1.05
    ,【
    0.99
    IS
    0.98
    AN
    0.95
    erView
    0.93
    LETE
    0.92
    ień
    0.91
    рита
    0.89
    رین
    0.89
    Activations Density 0.000%

    No Known Activations