© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62359
    Prev
    Next
    INDEX
    Explanations

    castle town, book, limousine bus

    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
    s
    0.56
    S
    0.51
    P
    0.50
    K
    0.48
             
    0.48
    Y
    0.48
    E
    0.47
    we
    0.47
    Պ
    0.46
    ından
    0.46
    POSITIVE LOGITS
     armed
    0.46
     অনুমতি
    0.46
     ν
    0.45
    aisie
    0.45
     armoured
    0.43
     unmodified
    0.42
     nourriture
    0.42
     ammunition
    0.42
     ہوا۔
    0.42
     unanswered
    0.41
    Activations Density 0.006%

    No Known Activations