© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249788
    Prev
    Next
    INDEX
    Explanations

    code formatting

    np_max-act-logits · gemini-2.5-flash-lite
    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
    we
    0.43
    work
    0.41
    «
    0.38
    constant
    0.37
    intr
    0.37
    귿
    0.37
    „
    0.36
    irre
    0.36
    yed
    0.36
                                  
    0.35
    POSITIVE LOGITS
    }:
    0.41
     ended
    0.39
     lowered
    0.39
    }->
    0.39
     innocence
    0.39
     irrelevant
    0.38
     disagreed
    0.38
    ített
    0.38
     erred
    0.38
    囉
    0.36
    Activations Density 0.001%

    No Known Activations