© 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. 143883
    Prev
    Next
    INDEX
    Explanations

    detects

    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
    ش
    1.98
    т
    1.96
    л
    1.88
    ин
    1.80
    ס
    1.68
     uczni
    1.66
    ле
    1.66
    ت
    1.63
    та
    1.59
    G
    1.58
    POSITIVE LOGITS
    in
    1.71
    (
    1.63
    inį
    1.39
     I
    1.25
    inę
    1.17
    ,
    1.15
    摖
    1.14
    "
    1.13
    rak
    1.12
    ritional
    1.11
    Activations Density 0.000%

    No Known Activations