© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227294
    Prev
    Next
    INDEX
    Explanations

    self-esteem &

    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_6_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
    that
    1.05
    ());
    0.89
     ότι
    0.80
     avevano
    0.79
    B
    0.79
    X
    0.78
     hanno
    0.75
     Ли
    0.73
     राहा
    0.73
     negativos
    0.71
    POSITIVE LOGITS
    INE
    1.13
    in
    1.00
    י
    0.93
    не
    0.86
    ;
    0.85
     proliferation
    0.82
     neoplas
    0.82
    ר
    0.82
     The
    0.82
     lesion
    0.81
    Activations Density 0.001%

    No Known Activations