© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33823
    Prev
    Next
    INDEX
    Explanations

    magic system types

    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_3_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
    ET
    0.58
     at
    0.57
    Firefox
    0.57
    नई
    0.56
    ))
    0.54
    )}}
    0.54
     suing
    0.54
    )">
    0.53
     corrid
    0.53
     Aniston
    0.53
    POSITIVE LOGITS
    ه
    0.80
    c
    0.78
    t
    0.64
    С
    0.61
    k
    0.60
    ع
    0.59
     பொருள்
    0.58
    O
    0.58
    。
    0.57
    cian
    0.57
    Activations Density 0.002%

    No Known Activations