© 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. 232027
    Prev
    Next
    INDEX
    Explanations

    odd jobs

    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
    Y
    1.06
    of
    1.05
     Of
    1.05
    <0x80>
    0.98
    াই
    0.93
    氀
    0.91
    क
    0.86
    al
    0.86
    ing
    0.85
    ’
    0.85
    POSITIVE LOGITS
     wasteland
    0.95
    ام
    0.92
    ید
    0.88
    ॉन
    0.88
     hangar
    0.80
     drivetrain
    0.80
     daemon
    0.80
     cadence
    0.80
    bleau
    0.80
     watchdog
    0.80
    Activations Density 0.000%

    No Known Activations