© 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. 7712
    Prev
    Next
    INDEX
    Explanations

    declarations, components, or technical keywords

    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
    ﻖ
    2.76
    স্থানের
    2.48
    ﻨ
    2.43
    ue
    2.31
    න්
    2.26
    ﻌ
    2.24
    घे
    2.23
    cón
    2.21
    स्पद
    2.14
    рни
    2.12
    POSITIVE LOGITS
    ೇತ್ರ
    2.64
    야
    2.57
    まるで
    2.37
    gpio
    2.37
     avut
    2.27
     ɖ
    2.24
     لنا
    2.17
     cáo
    2.15
    %%%%
    2.14
     fuelled
    2.13
    Activations Density 0.001%

    No Known Activations