© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37047
    Prev
    Next
    INDEX
    Explanations

    cause of negative outcomes

    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
    ل
    1.05
    ל
    0.84
    ри
    0.71
    ер
    0.67
    գ
    0.63
     aş
    0.62
     canister
    0.62
    अर्
    0.62
    ര്‍ച്ച
    0.62
    াল
    0.59
    POSITIVE LOGITS
     that
    0.74
    /
    0.72
    ,
    0.71
     acumul
    0.70
     of
    0.66
    ق
    0.65
    ation
    0.64
     sosial
    0.62
    ico
    0.60
    וס
    0.59
    Activations Density 0.026%

    No Known Activations