© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46152
    Prev
    Next
    INDEX
    Explanations

    no single right answer

    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_13_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
    戽
    0.67
    t
    0.65
    冀
    0.57
    うん
    0.57
     Catawiki
    0.53
     ọ
    0.52
    ូល
    0.52
     hemp
    0.51
    ｳ
    0.50
     zhī
    0.50
    POSITIVE LOGITS
     desirable
    0.53
     prestigious
    0.51
     Times
    0.51
     rerun
    0.51
     desired
    0.48
    IDs
    0.47
     specular
    0.46
    ided
    0.46
     celebrated
    0.46
     .
    0.45
    Activations Density 0.059%

    No Known Activations