© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37746
    Prev
    Next
    INDEX
    Explanations

    Paris Pass or Paris Peace

    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
    ა
    0.76
    мана
    0.71
    avez
    0.65
    LLCATS
    0.64
    ことなく
    0.63
    पी
    0.61
     সময়ে
    0.61
    earch
    0.59
    ため
    0.59
    expects
    0.59
    POSITIVE LOGITS
     on
    0.80
    '
    0.66
    }$
    0.61
    on
    0.59
    :
    0.59
    liche
    0.57
     On
    0.56
     checklist
    0.56
     Париж
    0.56
    <0x93>
    0.55
    Activations Density 0.006%

    No Known Activations