© 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. 144171
    Prev
    Next
    INDEX
    Explanations

    deluxe edition or Stamina

    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
    ્સ
    1.45
    ции
    1.25
    of
    1.20
    า
    1.19
    ется
    1.18
    सँग
    1.18
    owanie
    1.16
    smittel
    1.16
    𝘀
    1.09
    do
    1.07
    POSITIVE LOGITS
    ↵↵
    1.70
    ك
    1.55
    б
    1.52
    ل
    1.43
    غ
    1.27
    ам
    1.20
    一
    1.20
    I
    1.16
    لع
    1.15
    كثر
    1.14
    Activations Density 0.000%

    No Known Activations