© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100368
    Prev
    Next
    INDEX
    Explanations

    What does ... have to do

    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_14_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
    a
    0.53
    C
    0.53
    }-(\
    0.52
    an
    0.51
    -'
    0.51
     utterances
    0.51
    ிகள்
    0.50
    "=
    0.50
    -\{
    0.49
    Sel
    0.49
    POSITIVE LOGITS
     In
    0.57
     Información
    0.55
     تاز
    0.54
     Information
    0.54
    asă
    0.54
     Incoming
    0.53
     So
    0.52
    льным
    0.52
    ться
    0.51
     чи
    0.51
    Activations Density 0.003%

    No Known Activations