© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14406
    Prev
    Next
    INDEX
    Explanations

    aws iam resource identifiers

    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_40_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
    ́u
    0.41
     Checker
    0.39
     checker
    0.38
    checker
    0.37
    枞
    0.36
    Checker
    0.36
     تضيف
    0.34
    诃
    0.34
     років
    0.34
     checkers
    0.34
    POSITIVE LOGITS
    ,,
    0.38
    Fle
    0.38
     %%
    0.34
    Mono
    0.34
     বায়
    0.33
     கப்
    0.33
    ///
    0.33
    τέρα
    0.33
    \,
    0.32
    Accept
    0.32
    Activations Density 0.000%

    No Known Activations