© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138060
    Prev
    Next
    INDEX
    Explanations

    output redirection `>&`

    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_37_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
     Slice
    0.43
     Soft
    0.40
    Slice
    0.39
     soft
    0.38
    })$
    0.38
     commande
    0.38
     পুল
    0.37
     Commander
    0.37
    cmd
    0.37
    Soft
    0.37
    POSITIVE LOGITS
     Gama
    0.38
    responding
    0.38
     партії
    0.38
    掛
    0.37
     abre
    0.37
    agée
    0.36
    语
    0.35
    付ける
    0.34
     responding
    0.34
    Correction
    0.34
    Activations Density 0.002%

    No Known Activations