© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132786
    Prev
    Next
    INDEX
    Explanations

    Comstock Laws, Vegas, stock

    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
    \
    1.20
    ra
    1.05
    le
    0.98
    ter
    0.92
    ib
    0.91
    aj
    0.89
    话说
    0.85
     by
    0.83
    ys
    0.83
    不容易
    0.83
    POSITIVE LOGITS
    ў
    1.23
    UD
    1.11
    UN
    1.10
    ز
    1.09
    AB
    1.08
    UE
    1.06
    AN
    1.03
    ULONG
    1.02
    IR
    1.01
    AR
    0.99
    Activations Density 0.000%

    No Known Activations