© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196862
    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
     DR
    0.44
    Count
    0.40
     riguard
    0.39
    نده
    0.38
    maven
    0.37
    Disconnected
    0.37
     Lied
    0.37
     ['$
    0.37
    getCount
    0.37
    Predicate
    0.37
    POSITIVE LOGITS
    зии
    0.47
     shockingly
    0.44
     shocking
    0.43
    ana
    0.42
    aner
    0.42
    anna
    0.42
    anol
    0.42
    انا
    0.40
    ানা
    0.40
    iner
    0.40
    Activations Density 0.000%

    No Known Activations