© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252351
    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_56_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
    around
    0.43
     alrededor
    0.42
     attorno
    0.42
     sekitar
    0.40
     around
    0.39
     ረ
    0.39
     حول
    0.38
    代引き
    0.38
    ṡ
    0.37
    经销
    0.37
    POSITIVE LOGITS
     works
    0.44
     Works
    0.43
    Works
    0.41
     obras
    0.38
    obic
    0.37
    Encript
    0.36
     WORKS
    0.36
     heard
    0.36
    ěž
    0.36
    WholeProgram
    0.36
    Activations Density 0.000%

    No Known Activations