© 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. 208758
    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_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
     조합
    0.41
    вица
    0.39
     ჯ
    0.38
    อะ
    0.37
    bicyclo
    0.37
    AGRAM
    0.35
     sutures
    0.35
     époque
    0.35
     벡터
    0.34
    豬
    0.34
    POSITIVE LOGITS
    ní
    0.46
     rescued
    0.39
    ity
    0.39
    í
    0.37
     membangun
    0.36
    ')):
    0.36
    ীয়
    0.35
     bodyguard
    0.35
    upport
    0.34
     paramilitary
    0.34
    Activations Density 0.000%

    No Known Activations