© 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. 92754
    Prev
    Next
    INDEX
    Explanations

    scarecrow win award

    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
    5
    0.60
    cante
    0.55
    c
    0.53
    mp
    0.53
     जास्त
    0.51
    নিবেশ
    0.49
    6
    0.48
    荡
    0.48
    żą
    0.48
    P
    0.48
    POSITIVE LOGITS
     ideologies
    0.56
     pedals
    0.56
     parar
    0.55
     bravery
    0.54
     metode
    0.54
     subtitles
    0.54
     procesu
    0.54
     professor
    0.53
     sentiments
    0.51
     polypeptides
    0.51
    Activations Density 0.000%

    No Known Activations