© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 91823
    Prev
    Next
    INDEX
    Explanations

    you acknowledging positive regard

    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
    ônio
    0.66
    。「
    0.63
     fabriqu
    0.56
     toxins
    0.55
     boutons
    0.55
    ück
    0.54
    。『
    0.53
    。
    0.53
    ，
    0.52
    【
    0.52
    POSITIVE LOGITS
    c
    0.88
    e
    0.82
    etc
    0.77
    and
    0.73
    ed
    0.73
    es
    0.70
    et
    0.70
    esteem
    0.70
    d
    0.70
    AD
    0.69
    Activations Density 0.005%

    No Known Activations