© 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. 65379
    Prev
    Next
    INDEX
    Explanations

    remark/remarks

    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
    کنش
    0.38
    india
    0.36
     প্রহ
    0.36
    ENES
    0.35
    वरण
    0.34
     Randall
    0.34
    SIBILITIES
    0.34
    脯
    0.34
    rn
    0.33
    southeast
    0.33
    POSITIVE LOGITS
     remark
    2.53
     remarks
    2.28
     Remarks
    2.13
     remarque
    2.09
     remarked
    2.06
    remark
    2.06
    Remark
    1.98
    remarks
    1.98
    Remarks
    1.98
     Remark
    1.95
    Activations Density 0.127%

    No Known Activations