© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257852
    Prev
    Next
    INDEX
    Explanations

    `script`:

    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_22_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
     DR
    0.46
     P
    0.46
     POP
    0.45
     ഗ
    0.45
     Leagues
    0.44
     PUP
    0.43
     atteggi
    0.42
    XH
    0.42
     WhatsApp
    0.42
     Prim
    0.42
    POSITIVE LOGITS
    destination
    0.46
    minutes
    0.46
    your
    0.45
    澳大利
    0.43
    phosphory
    0.42
    ঞ্জে
    0.42
    kok
    0.41
     datth
    0.41
    㕸
    0.41
     செய்யுங்கள்
    0.40
    Activations Density 0.000%

    No Known Activations