© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88928
    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_23_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
     mes
    0.42
     نسب
    0.41
     sexu
    0.40
     fung
    0.40
     feminism
    0.40
     bestimmten
    0.40
     testosterone
    0.40
    }],
    0.39
     knowledge
    0.39
     Numer
    0.39
    POSITIVE LOGITS
    anyi
    0.48
    ثمان
    0.48
    gathered
    0.45
    ંધ
    0.44
    దిక
    0.44
     дорога
    0.43
     olhando
    0.43
    椋
    0.43
    फेल
    0.42
    ग्ध
    0.42
    Activations Density 0.000%

    No Known Activations