© 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. 8290
    Prev
    Next
    INDEX
    Explanations

    javascript node.js

    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
    ना
    2.19
    ۲
    2.14
    ainte
    2.12
    ۳
    2.08
     smack
    2.05
     доля
    1.98
    𝙩
    1.94
     fingertips
    1.92
    ने
    1.85
    陥
    1.82
    POSITIVE LOGITS
    د
    1.70
    }$)
    1.67
    oczes
    1.65
    менный
    1.61
    ೀರ
    1.61
    ו
    1.60
    咙
    1.58
     verbose
    1.56
    ᴢ
    1.55
    aklar
    1.52
    Activations Density 0.026%

    No Known Activations