© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 1419
    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_12_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
     ["
    0.38
     missile
    0.35
     ナイ
    0.35
     (\<
    0.32
     sanguin
    0.32
     Missile
    0.32
    !`
    0.32
     νε
    0.31
     Ti
    0.31
     []:
    0.31
    POSITIVE LOGITS
    cies
    0.40
    ygons
    0.40
    cił
    0.38
    isał
    0.38
    ترف
    0.35
    entie
    0.35
    ertos
    0.35
    ories
    0.33
     overhauled
    0.33
     merken
    0.33
    Activations Density 0.227%

    No Known Activations