© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33134
    Prev
    Next
    INDEX
    Explanations

    Native types of

    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_40_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
     Exper
    0.41
     well
    0.40
    ശു
    0.40
     प्रैक्ट
    0.39
    慢
    0.39
    Exper
    0.38
    well
    0.38
    গু
    0.38
     ശു
    0.38
     श्रेष्ठ
    0.37
    POSITIVE LOGITS
    kten
    0.38
    矾
    0.36
    Lib
    0.36
     berth
    0.36
    yt
    0.35
    のだ
    0.35
    riters
    0.35
     Burbank
    0.35
    marc
    0.35
    ult
    0.35
    Activations Density 0.000%

    No Known Activations