© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32894
    Prev
    Next
    INDEX
    Explanations

    or not

    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_31_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
    ائم
    0.36
    Min
    0.35
    Mary
    0.34
    heastern
    0.34
     amus
    0.34
    avais
    0.33
    제
    0.33
    ériment
    0.33
    eday
    0.33
    AIRMAN
    0.32
    POSITIVE LOGITS
     NOT
    0.61
    NOT
    0.59
    ではない
    0.57
    否
    0.55
     not
    0.54
     Nope
    0.54
    nope
    0.52
     değil
    0.52
    not
    0.49
     vs
    0.49
    Activations Density 0.033%

    No Known Activations