© 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. 7746
    Prev
    Next
    INDEX
    Explanations

    health concerns or income from

    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
     passer
    0.43
     parc
    0.43
     VCO
    0.41
    рафон
    0.40
    gano
    0.38
     recepción
    0.38
    歹
    0.38
    募
    0.37
     pharmac
    0.37
    ревно
    0.37
    POSITIVE LOGITS
    invasive
    0.41
    alba
    0.39
     economically
    0.38
     গোষ্ঠী
    0.38
    dom
    0.36
     cosy
    0.34
    groups
    0.34
     MIG
    0.33
    சிகள்
    0.33
    stimulating
    0.33
    Activations Density 0.011%

    No Known Activations