© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177257
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
    akili
    0.46
    URU
    0.44
    кую
    0.42
     problematic
    0.42
     Latvian
    0.42
    㫙
    0.42
     일반
    0.41
     ambiguity
    0.41
     hopeful
    0.41
     bibliographic
    0.41
    POSITIVE LOGITS
    lx
    0.52
    <i>
    0.49
     instilled
    0.44
    **
    0.43
     Supplemental
    0.43
     खिला
    0.40
    iveau
    0.40
    Supplemental
    0.40
    L
    0.40
    N
    0.39
    Activations Density 0.000%

    No Known Activations