© 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. 125252
    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_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
     వర్
    0.37
    itations
    0.36
    getItem
    0.36
     Che
    0.35
     args
    0.35
    matter
    0.34
     Ofer
    0.34
    ᾰ
    0.34
     matter
    0.34
     General
    0.33
    POSITIVE LOGITS
     beweg
    0.42
     springer
    0.40
    獾
    0.40
    ཊ
    0.39
     tabpos
    0.38
    㫙
    0.38
    豆
    0.37
     சிவப்பு
    0.37
     руха
    0.37
    recur
    0.37
    Activations Density 0.000%

    No Known Activations