© 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. 7247
    Prev
    Next
    INDEX
    Explanations

    hesitation and doubt

    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
    ра
    2.87
    𝐀
    2.63
    𝐧
    2.57
    𝐫
    2.56
    𝘢
    2.55
    𝓐
    2.55
    磋商
    2.54
    𝘰
    2.47
    𝐄
    2.43
    𝐅
    2.43
    POSITIVE LOGITS
    また
    2.46
    lessly
    2.44
    }'
    2.24
    क्या
    2.20
    }");
    2.18
    ión
    2.18
    на
    2.14
    গ্রস্ত
    2.11
    ствий
    2.07
    无疑
    2.06
    Activations Density 0.058%

    No Known Activations