© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259606
    Prev
    Next
    INDEX
    Explanations

    pleasure, stability, anhedonia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    uta
    0.58
     tempList
    0.56
    iguous
    0.54
     gigante
    0.53
    alanya
    0.52
    erate
    0.52
    ülle
    0.52
    v
    0.51
    vili
    0.51
    ateral
    0.51
    POSITIVE LOGITS
     microbiological
    0.76
     overclock
    0.70
     核
    0.68
     benzodiazep
    0.65
     carcinogenic
    0.65
     핵
    0.64
     microbiology
    0.64
     anod
    0.63
     isopropyl
    0.63
     généralement
    0.61
    Activations Density 0.000%

    No Known Activations