© 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. 33822
    Prev
    Next
    INDEX
    Explanations

    sprint goal

    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
    ни
    0.80
    𝐬
    0.70
    tahun
    0.66
    ال
    0.63
    ری
    0.63
    proteins
    0.63
    determined
    0.61
    ام
    0.59
    يل
    0.58
    ফস
    0.58
    POSITIVE LOGITS
    ﾞ
    0.60
    एस
    0.59
    কে
    0.58
    يح
    0.57
    RIP
    0.57
     prennent
    0.57
    Ю
    0.57
     αυ
    0.56
    ВИ
    0.56
     quail
    0.55
    Activations Density 0.008%

    No Known Activations