© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233794
    Prev
    Next
    INDEX
    Explanations

    German philosophy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Lep
    0.44
    fulfilled
    0.44
     lep
    0.42
     Lep
    0.40
    舎
    0.38
     Retour
    0.38
    Opel
    0.36
    beige
    0.36
    steelblue
    0.36
    opro
    0.35
    POSITIVE LOGITS
     F
    0.53
    RAY
    0.40
     liability
    0.39
     fxe
    0.39
     ນ
    0.39
     Phenomena
    0.38
     ຈ
    0.38
    និត
    0.37
     Philosophie
    0.37
    ctrine
    0.37
    Activations Density 0.008%

    No Known Activations