© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201473
    Prev
    Next
    INDEX
    Explanations

    Peaky Blinders

    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_6_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
     of
    1.32
    ק
    1.27
    י
    1.26
    า
    1.12
    ي
    1.11
     at
    1.09
    ד
    1.06
    лі
    1.03
     on
    1.02
    ح
    0.98
    POSITIVE LOGITS
     \
    1.10
    liness
    0.94
    sembles
    0.94
    liches
    0.87
    ises
    0.85
    fr
    0.84
    F
    0.84
    ue
    0.83
    lägg
    0.83
    flakes
    0.82
    Activations Density 0.000%

    No Known Activations