© 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. 37012
    Prev
    Next
    INDEX
    Explanations

    introducing a qualification

    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
     అ
    0.64
     ли
    0.64
     ත
    0.61
     городов
    0.61
     ентите
    0.58
     над
    0.58
     fruto
    0.58
     수는
    0.57
    љи
    0.57
    divide
    0.57
    POSITIVE LOGITS
    ad
    0.59
     on
    0.57
    OW
    0.57
    ORIA
    0.57
    on
    0.55
    u
    0.54
    AM
    0.54
     Critique
    0.53
    ان
    0.52
    MQ
    0.50
    Activations Density 0.004%

    No Known Activations