© 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. 36302
    Prev
    Next
    INDEX
    Explanations

    will be followed by an action

    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
    allas
    0.51
    ims
    0.50
    "
    0.50
    '
    0.49
     توسط
    0.48
     O
    0.46
     kemudian
    0.46
    liced
    0.45
    ampi
    0.45
    usuario
    0.45
    POSITIVE LOGITS
    PING
    0.55
    en
    0.53
    dU
    0.50
    ÈRE
    0.50
    ILERS
    0.50
    KAR
    0.49
    鮫
    0.48
    Woo
    0.48
    eraj
    0.48
     maximise
    0.48
    Activations Density 0.013%

    No Known Activations