© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31271
    Prev
    Next
    INDEX
    Explanations

    can be

    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
    lsen
    0.26
    ']==
    0.26
    abin
    0.25
    ght
    0.25
    yel
    0.24
    tyw
    0.23
     फी
    0.23
     جميل
    0.23
    友
    0.23
    oco
    0.23
    POSITIVE LOGITS
     способны
    0.25
    PLEASE
    0.25
     podendo
    0.25
    ಿಸಬಹುದು
    0.25
     winning
    0.24
     smi
    0.24
    ポジション
    0.24
     offended
    0.24
    硖
    0.24
     PLEASE
    0.24
    Activations Density 0.014%

    No Known Activations