© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150542
    Prev
    Next
    INDEX
    Explanations

    button related code

    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_23_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
     K
    0.20
     Day
    0.19
    ufficient
    0.18
     day
    0.18
     F
    0.18
     Contempor
    0.18
     STAT
    0.17
    icolor
    0.17
     GOOD
    0.17
     USO
    0.17
    POSITIVE LOGITS
    রাজনৈতিক
    0.21
     Opportun
    0.19
    Butterfly
    0.19
    璫
    0.19
    ધ
    0.19
    తి
    0.18
     vibhav
    0.18
    蝴蝶
    0.18
    recognizable
    0.18
    गें
    0.18
    Activations Density 0.002%

    No Known Activations