© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77144
    Prev
    Next
    INDEX
    Explanations

    finding `item` or `c` or `p` or `ner`

    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_31_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
    SizeType
    0.37
     উৎ
    0.32
     vét
    0.32
     Panamá
    0.31
     modalités
    0.31
     âgé
    0.31
    SIZ
    0.31
    藓
    0.30
     meme
    0.30
    ตู
    0.30
    POSITIVE LOGITS
     gale
    0.37
     thả
    0.35
     din
    0.34
    ctl
    0.33
     Compose
    0.33
     futuristic
    0.33
     Namespace
    0.33
     basket
    0.33
     porous
    0.32
    igest
    0.32
    Activations Density 0.002%

    No Known Activations