© 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. 91171
    Prev
    Next
    INDEX
    Explanations

    probabilities and transitions

    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
    of
    0.53
     Desenvolvimento
    0.51
    сным
    0.49
    ශ්‍ය
    0.49
     Asalamualaikum
    0.47
     раство
    0.47
     \%
    0.47
     Electroly
    0.44
    облада
    0.44
     Pediatr
    0.44
    POSITIVE LOGITS
     ठहर
    0.49
    verts
    0.46
    取締
    0.46
     ئۇ
    0.46
    fler
    0.45
     शुक्ल
    0.45
    ن
    0.45
    س
    0.45
     United
    0.44
    二百
    0.44
    Activations Density 0.000%

    No Known Activations