© 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. 108954
    Prev
    Next
    INDEX
    Explanations

    kleptomaniac, kleptomania, Kleizmer

    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
    g
    1.42
    p
    1.34
    گ
    1.29
    c
    1.23
    ية
    1.15
    ை
    1.14
    ра
    1.09
    ج
    1.09
    ४
    1.09
    ৫
    1.08
    POSITIVE LOGITS
     by
    1.73
    و
    1.40
    ]
    1.34
    ו
    1.14
    -
    1.13
    )
    1.08
     of
    1.02
     rins
    0.99
     второй
    0.95
     vapors
    0.95
    Activations Density 0.001%

    No Known Activations