© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67338
    Prev
    Next
    INDEX
    Explanations

    continuity and change

    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_46_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
     end
    2.59
     ended
    2.44
     ending
    2.39
     ends
    2.30
     끝
    2.27
     Ending
    2.17
    Ending
    2.17
    结束
    2.13
     Ends
    2.11
     END
    2.09
    POSITIVE LOGITS
    ijen
    0.38
    ويس
    0.37
    <unused92>
    0.36
    ựa
    0.35
    趔
    0.35
    riko
    0.34
     Alec
    0.34
     الانت
    0.33
    शीर
    0.33
     numerous
    0.33
    Activations Density 0.045%

    No Known Activations