© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41961
    Prev
    Next
    INDEX
    Explanations

    long-term strategy

    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_3_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
    تان
    0.75
    ۹
    0.66
    ﻠ
    0.66
    ﻥ
    0.64
    gallant
    0.62
    sendPluginResult
    0.61
    หนด
    0.60
    스럽
    0.60
    侔
    0.60
     αυτο
    0.59
    POSITIVE LOGITS
    ang
    1.24
    ay
    0.96
    em
    0.86
    om
    0.86
    ai
    0.85
    <0x0D>
    0.84
    am
    0.83
    ో
    0.82
    ur
    0.81
    ab
    0.78
    Activations Density 0.000%

    No Known Activations