© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161013
    Prev
    Next
    INDEX
    Explanations

    fundamental

    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
    O
    1.17
     at
    1.11
    F
    1.10
    ’
    1.08
    IC
    1.07
    manship
    1.06
    ED
    1.05
    memorial
    1.04
    AK
    1.02
    AC
    1.00
    POSITIVE LOGITS
    ли
    1.70
     I
    1.45
    ۔
    1.31
    是
    1.27
    ።
    1.23
    ים
    1.20
    í
    1.19
    1.18
    า
    1.15
    é
    1.14
    Activations Density 0.001%

    No Known Activations