© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3184
    Prev
    Next
    INDEX
    Explanations

    willing willing mortals sex slaves

    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_5_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
    dır
    1.92
    ह
    1.90
    การ
    1.85
    س
    1.83
    с
    1.83
     ​​​​
    1.78
    ोल
    1.71
     версии
    1.67
    𝐠
    1.66
    у
    1.66
    POSITIVE LOGITS
     GIS
    2.09
    ivity
    1.97
     vicinity
    1.95
    ició
    1.92
    eel
    1.89
    ionante
    1.83
     bores
    1.82
     thrombocyt
    1.79
     iterates
    1.78
    stones
    1.78
    Activations Density 0.000%

    No Known Activations