© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116310
    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_27_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
    ière
    0.42
    ançois
    0.39
    ich
    0.38
    spf
    0.37
    };//
    0.37
     وبالتالي
    0.36
    <strong>
    0.36
    edo
    0.35
    istico
    0.35
    e
    0.35
    POSITIVE LOGITS
     SOME
    0.43
     المر
    0.38
     disrupting
    0.38
     retained
    0.37
     supernatant
    0.37
     disruption
    0.37
     EFFECT
    0.37
     undecided
    0.37
     limitation
    0.37
    Notation
    0.37
    Activations Density 0.000%

    No Known Activations