© 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. 7623
    Prev
    Next
    INDEX
    Explanations

    collecting and diffing

    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
    𝗁
    1.28
    𝑟
    1.24
    𝑚
    1.22
    𝑐
    1.20
    ᴛ
    1.20
    𝑅
    1.20
    ﺩ
    1.19
    ૪
    1.18
    ﻣ
    1.17
    𝑝
    1.15
    POSITIVE LOGITS
    en
    1.31
    in
    1.04
    it
    0.99
     enact
    0.97
    er
    0.93
    ou
    0.93
    Chol
    0.92
    de
    0.91
     affinity
    0.91
    et
    0.90
    Activations Density 0.017%

    No Known Activations