© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1369
    Prev
    Next
    INDEX
    Explanations

    code syntax declaration

    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
    ാവ
    0.41
     üld
    0.40
     ä
    0.38
    蛾
    0.36
     keySchedule
    0.36
    瓜
    0.35
    チャ
    0.34
    ধিক
    0.34
    ("&
    0.34
     wedge
    0.34
    POSITIVE LOGITS
    culaire
    0.43
    endi
    0.40
    hors
    0.38
     projet
    0.38
    Dur
    0.38
    comprom
    0.37
    phrase
    0.36
     animales
    0.36
     espagn
    0.36
    transmit
    0.36
    Activations Density 0.007%

    No Known Activations