© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182273
    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_29_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
    вовано
    0.42
    벗
    0.41
     makeSound
    0.40
    funeral
    0.40
    perception
    0.38
     bays
    0.38
    Median
    0.38
    jersey
    0.38
     meat
    0.38
    agriculture
    0.38
    POSITIVE LOGITS
    দান
    0.44
    IGO
    0.42
     duit
    0.39
     பரிசு
    0.37
    ิท
    0.35
    랄
    0.35
    icia
    0.35
    ப்படும்
    0.35
     পাওয়া
    0.34
     μετά
    0.34
    Activations Density 0.000%

    No Known Activations