© 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. 122396
    Prev
    Next
    INDEX
    Explanations

    despotism, Tutan, Desmos, despising

    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
    У
    0.72
    an
    0.69
    ان
    0.68
    מ
    0.68
     toque
    0.66
    كل
    0.66
    quela
    0.64
    ن
    0.64
    ال
    0.63
    па
    0.63
    POSITIVE LOGITS
    ications
    0.62
    ic
    0.59
    بین
    0.59
    Zj
    0.58
    یم
    0.57
     पत्र
    0.56
    identification
    0.55
    DbContext
    0.55
    gne
    0.54
    @]
    0.54
    Activations Density 0.000%

    No Known Activations