© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9476
    Prev
    Next
    INDEX
    Explanations

    touch contact

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     রাজধানী
    0.69
    μο
    0.65
    मन
    0.63
    MF
    0.63
    周年
    0.63
    აქ
    0.62
    ది
    0.62
     把
    0.62
    GS
    0.62
     DSC
    0.62
    POSITIVE LOGITS
     touching
    2.21
     touch
    2.06
    touch
    2.03
    Touch
    1.95
     touches
    1.95
     Touch
    1.86
     contact
    1.82
     Touching
    1.78
    contact
    1.76
     TOUCH
    1.75
    Activations Density 0.275%

    No Known Activations