© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158703
    Prev
    Next
    INDEX
    Explanations

    flakiness

    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_2_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
    n
    1.89
    ла
    1.73
    ת
    1.63
    al
    1.54
    ל
    1.54
    -
    1.45
    ש
    1.42
    то
    1.41
    is
    1.38
    ли
    1.38
    POSITIVE LOGITS
    Ａ
    1.17
     as
    1.07
    Ｃ
    1.05
    ：
    0.95
     đầu
    0.95
    }=
    0.93
    ^{*}
    0.92
    Ｌ
    0.89
     és
    0.88
    Ｅ
    0.88
    Activations Density 0.001%

    No Known Activations