© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208486
    Prev
    Next
    INDEX
    Explanations

    caret symbol

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     რამდ
    0.43
     méthod
    0.42
     precursor
    0.39
     ‘
    0.39
     regl
    0.38
     admiss
    0.38
     տար
    0.36
     bread
    0.35
     impos
    0.35
     marshmallow
    0.34
    POSITIVE LOGITS
    {$
    0.43
    {
    0.42
    none
    0.38
     {
    0.36
    NONE
    0.36
    {(
    0.36
    •
    0.35
     {$
    0.35
     NONE
    0.35
    пин
    0.35
    Activations Density 0.000%

    No Known Activations