© 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. 82350
    Prev
    Next
    INDEX
    Explanations

    agradable, CGRect, Grâce, giấc mơ

    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
     are
    1.96
    ية
    1.94
    ك
    1.58
     can
    1.52
     be
    1.48
    ка
    1.44
    ut
    1.34
    c
    1.27
    ab
    1.24
    ia
    1.16
    POSITIVE LOGITS
    ی
    1.79
    9
    1.65
    is
    1.55
    نی
    1.53
    ม
    1.53
    ות
    1.45
    6
    1.41
    ites
    1.40
    ,
    1.31
    8
    1.30
    Activations Density 0.000%

    No Known Activations