© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134989
    Prev
    Next
    INDEX
    Explanations

    database configuration

    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_1_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
    0
    1.10
     i
    1.05
    O
    1.05
    ۰
    0.94
    2
    0.87
     you
    0.83
    iva
    0.83
    OB
    0.82
    Ns
    0.82
    ۰۰
    0.81
    POSITIVE LOGITS
    in
    1.74
    ки
    1.25
    ન
    1.24
    ł
    1.17
    is
    1.16
    л
    1.16
    在
    1.15
     in
    1.14
    ين
    1.13
    א
    1.13
    Activations Density 0.000%

    No Known Activations