© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245284
    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_40_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
     लेखन
    0.41
    lust
    0.37
    icier
    0.37
     pasado
    0.36
    国土
    0.36
    숱
    0.36
     Greenwich
    0.36
     chấm
    0.35
    encement
    0.35
     elapsed
    0.34
    POSITIVE LOGITS
    jne
    0.44
     parental
    0.40
     proteine
    0.39
    Peq
    0.38
    োলজি
    0.38
     пові
    0.38
     pove
    0.37
     Inter
    0.36
    Hib
    0.36
     줄
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.