© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79235
    Prev
    Next
    INDEX
    Explanations

    un prefix

    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_29_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
    प्तान
    0.37
    arrage
    0.36
    𝙙
    0.36
    xssf
    0.35
    韶
    0.34
    ulently
    0.34
    LAGAB
    0.34
    aurant
    0.33
    지요
    0.33
     venire
    0.33
    POSITIVE LOGITS
    cel
    0.33
     Cel
    0.32
    清潔
    0.32
     både
    0.32
    Cel
    0.32
     nějak
    0.32
     К
    0.32
     cael
    0.31
     complaint
    0.30
     tears
    0.30
    Activations Density 0.011%

    No Known Activations