© 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. 7564
    Prev
    Next
    INDEX
    Explanations

    size_t declarations

    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
    ﻲ
    2.58
    ु
    2.40
    ے
    2.33
    िक
    2.30
    ع
    2.24
    с
    2.16
     Oed
    2.08
    أ
    2.06
    ge
    2.01
    𝒌
    2.00
    POSITIVE LOGITS
    ไซต์
    2.33
    kaç
    2.25
     решить
    2.25
     Gelegenheit
    2.24
    britannien
    2.19
    স
    2.10
    maßen
    2.09
     поставить
    2.07
     supremacy
    2.06
    leistungen
    2.06
    Activations Density 0.024%

    No Known Activations