© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236442
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure markers

    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_25_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
     говорится
    0.25
     тоже
    0.23
    trasound
    0.23
    佛
    0.22
    opard
    0.22
     amoureux
    0.22
     biologiques
    0.22
     sqlType
    0.22
    }}$,
    0.21
    issense
    0.21
    POSITIVE LOGITS
     great
    0.27
     certain
    0.24
    ಳ್ಳ
    0.23
    ในการ
    0.23
     long
    0.23
     fusing
    0.23
     xu
    0.23
     Bryn
    0.22
     សូម
    0.22
     far
    0.22
    Activations Density 0.001%

    No Known Activations