© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133292
    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_50_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
    }--
    0.39
    scode
    0.39
    Prel
    0.38
    }.",
    0.38
    ESO
    0.38
     HOSP
    0.38
     afstand
    0.36
     Nyl
    0.36
     vy
    0.36
    ingham
    0.36
    POSITIVE LOGITS
     Valence
    0.40
     Sterile
    0.39
     Banks
    0.38
     रिपीट
    0.37
     Spray
    0.37
    Emerald
    0.37
     mutilated
    0.37
    <0x82>
    0.36
     бла
    0.36
    ជ្
    0.36
    Activations Density 0.000%

    No Known Activations