© 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. 2760
    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
    ร์
    2.52
    ه
    2.42
     få
    2.40
    <bos>
    2.29
    olutely
    2.25
    во
    2.22
    ة
    2.20
    মান
    2.12
    jenigen
    2.11
    এছ
    2.10
    POSITIVE LOGITS
    ان
    2.52
    स
    2.41
    AsyncKeyState
    2.41
    ﹡
    2.38
    一个
    2.36
    %=
    2.35
    缈
    2.34
     sinusoidal
    2.34
     '#'
    2.30
    fälle
    2.29
    Activations Density 0.212%

    No Known Activations