© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78066
    Prev
    Next
    INDEX
    Explanations

    say "**"

    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_53_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
    uco
    0.38
     nullable
    0.34
     HINSTANCE
    0.34
     BOOL
    0.34
    ন্ধ
    0.34
    think
    0.34
     &#
    0.34
    सलमान
    0.34
     주인
    0.33
    ης
    0.33
    POSITIVE LOGITS
    veni
    0.40
    æk
    0.39
    Ц
    0.38
     rolls
    0.38
     probes
    0.38
    제를
    0.36
    सीबी
    0.36
    abei
    0.35
    साहेब
    0.35
     روبل
    0.35
    Activations Density 0.027%

    No Known Activations