© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145302
    Prev
    Next
    INDEX
    Explanations

    forum shopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ة
    1.19
    ت
    1.18
    jší
    1.12
    .</
    1.06
    खास्त
    1.06
    .”
    1.04
    OL
    1.01
     està
    1.00
    กับ
    1.00
    ável
    0.98
    POSITIVE LOGITS
    w
    1.71
     is
    1.63
    ן
    1.60
    ا
    1.56
    ки
    1.51
    0
    1.49
    were
    1.48
    in
    1.45
    ский
    1.45
    ר
    1.44
    Activations Density 0.000%

    No Known Activations