© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138802
    Prev
    Next
    INDEX
    Explanations

    Anya Sharma

    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
     с
    0.61
     време
    0.59
    ние
    0.55
     различ
    0.55
    ът
    0.55
     воде
    0.55
    г
    0.55
     председа
    0.55
     cried
    0.54
     rév
    0.54
    POSITIVE LOGITS
    ینس
    0.59
    ப்பான்
    0.58
    un
    0.57
     Americana
    0.55
    ח
    0.55
     Dixie
    0.54
    共有
    0.53
     ビジネス
    0.52
    LOTREntity
    0.52
     Zeus
    0.51
    Activations Density 0.000%

    No Known Activations