© 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. 6498
    Prev
    Next
    INDEX
    Explanations

    endogenous

    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
    াক্তন
    3.40
    ভৃতি
    3.29
    er
    2.96
    াকৃতিক
    2.86
    ER
    2.83
    ০০
    2.75
    $$\
    2.62
    ी
    2.59
    வும்
    2.59
    য়োজন
    2.58
    POSITIVE LOGITS
     sekali
    2.92
     veuillez
    2.68
     masy
    2.67
    ння
    2.64
     tongs
    2.63
     основ
    2.63
    قبال
    2.60
    σ
    2.59
     gewoon
    2.58
    annabin
    2.51
    Activations Density 0.037%

    No Known Activations