© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5005
    Prev
    Next
    INDEX
    Explanations

    practice and tutorial content

    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
     args
    0.38
    JECTION
    0.36
    ਣ
    0.35
     Blow
    0.34
    နှုန်း
    0.34
     arg
    0.33
    )}.
    0.33
    lectual
    0.33
     Breit
    0.32
    蝿
    0.32
    POSITIVE LOGITS
     क्वेश्चंस
    0.47
    Altri
    0.44
     probleme
    0.42
     질
    0.41
     problems
    0.41
     problemas
    0.40
    लब्
    0.40
     PROBLEMS
    0.40
    नर
    0.39
     ट्रेस
    0.39
    Activations Density 0.045%

    No Known Activations