© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177211
    Prev
    Next
    INDEX
    Explanations

    refutable, violation, disrespectful, lost

    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_24_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
     egot
    0.40
     bâ
    0.36
     ভগব
    0.35
     prede
    0.35
     प्रतिभाशाली
    0.35
    Ꮰ
    0.35
     antis
    0.34
     thug
    0.34
     automl
    0.34
     slot
    0.34
    POSITIVE LOGITS
    花了
    0.44
     Industries
    0.42
     (€
    0.41
    ales
    0.40
    orce
    0.40
    Indust
    0.39
    aspx
    0.39
    原因是
    0.38
     Mining
    0.38
    ês
    0.37
    Activations Density 0.000%

    No Known Activations