© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149398
    Prev
    Next
    INDEX
    Explanations

    code accumulation or calculation

    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_23_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
    ,-
    0.37
     >
    0.35
    -"
    0.34
    Seit
    0.33
    ="
    0.31
     hitt
    0.31
     =
    0.31
    Id
    0.31
     mittlerweile
    0.30
     More
    0.30
    POSITIVE LOGITS
     incipient
    0.34
     treatise
    0.33
    渭
    0.31
    早期
    0.31
     poseen
    0.31
     fieldContext
    0.30
     масла
    0.30
    苾
    0.30
     meticul
    0.30
     biosynthesis
    0.30
    Activations Density 0.001%

    No Known Activations