© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82831
    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_53_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
    Franz
    0.49
    endige
    0.40
    াশ
    0.38
    deren
    0.38
     coerce
    0.38
     گوئی
    0.38
    coerce
    0.37
    쭌
    0.37
     फ्लाई
    0.36
     बताए
    0.36
    POSITIVE LOGITS
     cond
    0.40
    COL
    0.40
     cap
    0.38
    <0xC2>
    0.38
     implication
    0.38
     login
    0.38
     hag
    0.38
    icosa
    0.36
     capt
    0.36
     hagg
    0.36
    Activations Density 0.000%

    No Known Activations