© 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. 7170
    Prev
    Next
    INDEX
    Explanations

    html head tag

    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
    𝑰
    2.01
    р
    1.97
    т
    1.91
    hips
    1.74
     hashedPassword
    1.73
    tio
    1.72
    𝑬
    1.70
    curr
    1.69
    functioning
    1.65
    reff
    1.64
    POSITIVE LOGITS
    न
    1.90
    ции
    1.87
    अल
    1.67
     ゙
    1.64
     jungle
    1.63
    狡
    1.55
     ERK
    1.54
    స్
    1.53
    ę
    1.53
     digamos
    1.53
    Activations Density 0.003%

    No Known Activations