© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1264
    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
    ены
    2.59
    們
    2.32
    (:,
    2.24
    tered
    2.18
    ش
    2.16
    ם
    2.14
    다면
    2.12
    ಾ
    2.07
     asterisk
    2.04
     solubility
    2.03
    POSITIVE LOGITS
    s
    2.82
    sah
    2.63
    sph
    2.62
    sos
    2.60
    පා
    2.53
    sit
    2.52
    snd
    2.44
    ের
    2.42
    sure
    2.41
    ython
    2.40
    Activations Density 0.103%

    No Known Activations