© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197549
    Prev
    Next
    INDEX
    Explanations

    putsch, gooey, tay

    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_4_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
    f
    1.30
    h
    1.11
    E
    1.10
    </h3>
    1.06
    AM
    1.04
    I
    1.03
    ON
    1.01
    l
    1.01
    OB
    1.00
    ELL
    0.99
    POSITIVE LOGITS
    io
    1.09
    یم
    1.05
    ”)
    1.01
    ’)
    0.96
    ین
    0.95
    یا
    0.94
    ’
    0.86
    ”).
    0.83
    ے
    0.82
    ”
    0.82
    Activations Density 0.005%

    No Known Activations