© 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. 206058
    Prev
    Next
    INDEX
    Explanations

    os or args with commands

    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
    N
    0.84
    am
    0.80
    Neces
    0.75
    OfInterest
    0.74
    cription
    0.73
     FODC
    0.73
    S
    0.71
    Reg
    0.70
    Score
    0.70
    Deg
    0.70
    POSITIVE LOGITS
     was
    1.09
    т
    0.96
     be
    0.91
    ر
    0.91
    ся
    0.91
    <0xA6>
    0.87
     to
    0.87
    р
    0.86
    IAN
    0.85
    ä
    0.84
    Activations Density 0.000%

    No Known Activations