© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61267
    Prev
    Next
    INDEX
    Explanations

    sense of

    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_11_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
     Just
    0.61
     Functions
    0.58
    ന്മ
    0.56
    are
    0.55
    Just
    0.55
    鍘
    0.54
    or
    0.53
     refunds
    0.53
    Functions
    0.52
    ログ
    0.52
    POSITIVE LOGITS
     degrade
    0.66
    <0x98>
    0.62
    <0x97>
    0.60
    <0x92>
    0.59
    ');
    0.59
    "),
    0.58
     máquina
    0.58
     versões
    0.58
    <0x96>
    0.57
     degraded
    0.57
    Activations Density 0.011%

    No Known Activations