© 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. 92811
    Prev
    Next
    INDEX
    Explanations

    ## Deep Dive

    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
    ed
    0.63
    }">
    0.58
     Reserva
    0.55
     Pony
    0.55
     मुआव
    0.54
     ఏర్ప
    0.54
     Sebuah
    0.52
     Mga
    0.52
     mayors
    0.52
    "^
    0.52
    POSITIVE LOGITS
    Like
    0.54
    ஷி
    0.52
    biased
    0.51
    יום
    0.50
    like
    0.50
    blue
    0.49
    widehat
    0.49
    Press
    0.48
    ʿ
    0.48
    Dome
    0.48
    Activations Density 0.011%

    No Known Activations