© 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. 6234
    Prev
    Next
    INDEX
    Explanations

    nsfw

    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
    و
    4.22
     나서
    3.06
    jenigen
    2.69
     apoi
    2.67
    帙
    2.66
    スカート
    2.45
    ו
    2.39
     desses
    2.38
    ಾಟ
    2.34
     ότι
    2.31
    POSITIVE LOGITS
    𝚘
    2.74
    𝚝
    2.73
    clarinet
    2.66
    ন্তন
    2.66
    𝒔
    2.64
    𝚞
    2.57
    𝓮
    2.56
    𝚎
    2.54
    й
    2.49
    𝒐
    2.49
    Activations Density 0.014%

    No Known Activations