© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196543
    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_4_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
    ص
    0.57
    it
    0.54
    Ana
    0.53
    Ela
    0.53
    सी
    0.50
    An
    0.46
    )
    0.46
    il
    0.45
    Fam
    0.45
    Anna
    0.45
    POSITIVE LOGITS
     rift
    0.54
     dismay
    0.51
     f
    0.50
     batt
    0.50
     ಅರ್ಜಿ
    0.49
     titanium
    0.49
     lleva
    0.49
     reopened
    0.49
     factor
    0.49
     เว
    0.49
    Activations Density 0.000%

    No Known Activations