© 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. 30726
    Prev
    Next
    INDEX
    Explanations

    included

    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
     खल
    0.33
    区分
    0.32
    Der
    0.32
    Oc
    0.31
    ccco
    0.31
    CCA
    0.31
    Fil
    0.30
    ⭒
    0.30
     に対
    0.30
    が
    0.30
    POSITIVE LOGITS
     நிலையில்
    0.34
     तहरीर
    0.32
     sensores
    0.32
     arbitrator
    0.32
     statuses
    0.31
     Bloody
    0.31
     पड़ी
    0.31
    醇
    0.31
     bloody
    0.31
     StatusBar
    0.30
    Activations Density 0.042%

    No Known Activations