© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38366
    Prev
    Next
    INDEX
    Explanations

    `reinterpret_cast`

    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_11_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
    Ин
    0.70
    З
    0.70
    Э
    0.66
    أ
    0.66
    ца
    0.64
    Пре
    0.64
    И
    0.64
    الت
    0.63
    или
    0.63
    Если
    0.63
    POSITIVE LOGITS
     colonial
    0.54
     GI
    0.54
     show
    0.54
     Championship
    0.52
     I
    0.51
     ceramic
    0.50
     shear
    0.50
     Universities
    0.50
     natural
    0.49
     dump
    0.49
    Activations Density 0.000%

    No Known Activations