© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175589
    Prev
    Next
    INDEX
    Explanations

    jab, jib, codes

    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_24_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
    닳
    0.25
     dựa
    0.24
     遊
    0.24
     Calcd
    0.24
    ifelse
    0.24
     ligados
    0.23
     pushing
    0.23
     createNative
    0.23
     into
    0.22
    🚢
    0.22
    POSITIVE LOGITS
    2
    0.28
    Sch
    0.26
    Sam
    0.25
    North
    0.25
    Ко
    0.25
    Ни
    0.25
    Algun
    0.24
    Rob
    0.24
    मह
    0.24
    Terror
    0.24
    Activations Density 0.002%

    No Known Activations