© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3764
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    or
    2.68
    ما
    2.64
    ЛИ
    2.52
     trav
    2.52
    u
    2.48
    íte
    2.40
    ن
    2.38
    ে
    2.29
    }$$
    2.27
    াধিক
    2.24
    POSITIVE LOGITS
    ll
    3.18
     Lordships
    3.10
     fleste
    2.96
    ר
    2.69
    貌
    2.64
    tl
    2.56
    llllllll
    2.54
     devenue
    2.53
    looms
    2.51
    ス
    2.50
    Activations Density 0.103%

    No Known Activations