© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134488
    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
     ट्रैक्टर
    0.40
     എഴു
    0.38
     Strategic
    0.38
     covering
    0.36
     CRO
    0.36
    夆
    0.35
    Strategic
    0.35
    ጸ
    0.35
    ofo
    0.35
     Genesis
    0.35
    POSITIVE LOGITS
    Tail
    0.40
    ంధ
    0.39
    हाबाद
    0.39
     местного
    0.39
    tails
    0.38
    }:=
    0.38
     ইন্দুর
    0.38
    katkan
    0.38
     depósito
    0.37
    かん
    0.36
    Activations Density 0.000%

    No Known Activations