© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201121
    Prev
    Next
    INDEX
    Explanations

    pain and suffering and damages

    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_12_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
    Calc
    0.54
    </strong>
    0.51
    And
    0.50
    <strong>
    0.49
    ’
    0.49
    4
    0.48
    ș
    0.48
    タ
    0.47
    ang
    0.46
    <sup>
    0.45
    POSITIVE LOGITS
     diperoleh
    0.54
     која
    0.50
    });
    0.49
     $("
    0.49
     通过
    0.48
     evidentiary
    0.47
     തുടങ്ങി
    0.47
    <unused1062>
    0.47
     ಒಳ್ಳ
    0.47
     $'
    0.47
    Activations Density 0.001%

    No Known Activations