© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8111
    Prev
    Next
    INDEX
    Explanations

    variable names after input

    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
    ीय
    0.88
    leştir
    0.87
     برانيه
    0.85
    யா
    0.83
    ಯಲ್ಲಿ
    0.83
    ljen
    0.80
     chão
    0.79
    𝘸
    0.77
    lene
    0.77
    വ
    0.75
    POSITIVE LOGITS
    та
    1.05
    कर
    0.99
    ق
    0.97
    на
    0.97
     torus
    0.84
     ores
    0.84
    za
    0.82
    ção
    0.81
     bounds
    0.80
     yarns
    0.79
    Activations Density 0.001%

    No Known Activations