© 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. 110633
    Prev
    Next
    INDEX
    Explanations

    SoC

    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
    '
    1.43
    '};
    0.96
    '!
    0.93
    '">
    0.89
     Интер
    0.89
    Cw
    0.89
    '=
    0.88
    Ln
    0.85
    \,\
    0.84
     Бе
    0.83
    POSITIVE LOGITS
    ल
    1.49
    0
    1.32
    та
    1.29
    ش
    1.28
    ні
    1.25
    ש
    1.25
    л
    1.21
    ون
    1.19
    การ
    1.19
    á
    1.18
    Activations Density 0.000%

    No Known Activations