© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159331
    Prev
    Next
    INDEX
    Explanations

    fat and related discussions

    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_2_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
     for
    1.60
     I
    1.34
    Α
    1.25
    ’
    1.21
    1.18
    :
    1.16
    ?,
    1.15
    ade
    1.12
    ه
    1.09
     R
    1.05
    POSITIVE LOGITS
    на
    1.48
    ת
    1.34
    い
    1.31
    ل
    1.17
    ripción
    1.16
    ح
    1.16
    ре
    1.15
    ナ
    1.12
    ため
    1.10
    ä
    1.05
    Activations Density 0.003%

    No Known Activations