© 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. 8035
    Prev
    Next
    INDEX
    Explanations

    Consumer Reports

    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
     исправ
    2.58
    𝐦
    2.39
    การ
    2.29
    с
    2.19
    нием
    2.19
    ن
    2.15
    }$.
    2.15
    人员
    2.13
     вр
    2.12
     बदलाव
    2.06
    POSITIVE LOGITS
    er
    2.88
    ية
    2.79
    ia
    2.52
     lymphatiques
    2.51
    ва
    2.49
     getroffen
    2.46
     longtemps
    2.46
    д
    2.44
    اپنی
    2.43
     eficaz
    2.39
    Activations Density 0.000%

    No Known Activations