© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91772
    Prev
    Next
    INDEX
    Explanations

    server room

    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_3_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
    لي
    0.58
    }{
    0.57
    2
    0.57
    ari
    0.55
    }.
    0.55
    ويه
    0.54
    }(
    0.53
    議員
    0.53
    িম
    0.52
     حين
    0.52
    POSITIVE LOGITS
     serves
    0.92
     servir
    0.89
     served
    0.86
    er
    0.82
     serving
    0.81
    Serve
    0.81
     serv
    0.79
     sirven
    0.77
    ing
    0.76
    on
    0.75
    Activations Density 0.001%

    No Known Activations