© 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. 34498
    Prev
    Next
    INDEX
    Explanations

    dumpster diving or dumpster fire

    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
    作った
    0.58
    I
    0.56
    輋
    0.55
     করেছিলাম
    0.52
    鋆
    0.52
    प्रमाणे
    0.51
     deswegen
    0.51
     (
    0.51
    Ǘ
    0.50
    Ꭽ
    0.49
    POSITIVE LOGITS
    د
    0.71
    ون
    0.69
    ）
    0.65
    ol
    0.63
    ুম
    0.63
    。）
    0.63
    )、
    0.61
    ਸ਼ਨ
    0.61
    ام
    0.60
    وم
    0.60
    Activations Density 0.000%

    No Known Activations