© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7051
    Prev
    Next
    INDEX
    Explanations

    pantera, pansexual, panning

    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_3_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
     государства
    1.89
    en
    1.87
     stelle
    1.83
    시키는
    1.80
    więks
    1.79
    sic
    1.76
    ี
    1.71
     dotyczą
    1.70
    collectionView
    1.70
     listOf
    1.67
    POSITIVE LOGITS
    ة
    1.92
    ッグ
    1.87
    िफिशियल
    1.71
    ேத்க
    1.70
    ि
    1.67
    )$\
    1.60
    ׂ
    1.58
    $('.
    1.52
     горе
    1.52
    vať
    1.51
    Activations Density 0.007%

    No Known Activations