© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119966
    Prev
    Next
    INDEX
    Explanations

    Should have

    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_27_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
    ص
    0.46
    ssel
    0.46
    もので
    0.46
    సూ
    0.46
    sson
    0.45
    ;
    0.45
    لم
    0.44
    先后
    0.44
    ство
    0.44
    సి
    0.43
    POSITIVE LOGITS
    войства
    0.47
    talking
    0.46
     recibirá
    0.46
    മൂഹ
    0.46
    metals
    0.45
     المملكة
    0.44
    кономски
    0.43
    Murder
    0.43
    葚
    0.43
    counting
    0.43
    Activations Density 0.012%

    No Known Activations