© 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. 7867
    Prev
    Next
    INDEX
    Explanations

    quoting

    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
    к
    2.79
     epileptic
    2.33
     коэффициент
    2.32
    ък
    2.32
    heit
    2.30
    Veja
    2.29
    ighi
    2.28
     subsistence
    2.28
    як
    2.26
     khắc
    2.25
    POSITIVE LOGITS
    𝖘
    2.95
    ⮚
    2.89
    𝗌
    2.87
    𝖚
    2.85
    𝖾
    2.74
     segi
    2.65
    𝐛
    2.59
    𝗋
    2.58
    𝗈
    2.55
    𝖽
    2.53
    Activations Density 0.001%

    No Known Activations