© 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. 157500
    Prev
    Next
    INDEX
    Explanations

    ending with -US, -(, -ENT, -ATES, -RES, -ZE, -SE, -ENTE, -ED

    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
    FI
    1.23
    BI
    1.22
    MI
    1.06
    5
    1.05
    PI
    0.98
    GI
    0.96
    のは
    0.93
    0
    0.93
     menjalani
    0.89
    TI
    0.88
    POSITIVE LOGITS
    k
    1.60
    h
    1.56
    f
    1.51
    v
    1.48
    t
    1.39
    c
    1.39
    ي
    1.38
    b
    1.35
    st
    1.22
    da
    1.19
    Activations Density 0.008%

    No Known Activations