© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149515
    Prev
    Next
    INDEX
    Explanations

    work hours or shift options

    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
     peacetime
    0.44
    doors
    0.38
     concave
    0.37
     assisted
    0.37
     तळ
    0.37
     scrub
    0.36
    গুলোকে
    0.36
    꺽
    0.36
     règ
    0.35
     flagpole
    0.35
    POSITIVE LOGITS
     Las
    0.44
    ewel
    0.44
     diffusion
    0.42
     Diffusion
    0.41
     hes
    0.41
     quarts
    0.40
    தியாக
    0.40
    Diffusion
    0.40
    ருங்கள்
    0.39
    Las
    0.39
    Activations Density 0.000%

    No Known Activations