© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257709
    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_10_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
     teamTable
    1.34
     ornaments
    1.32
    뽕
    1.25
     syllable
    1.23
    ात
    1.21
    ПР
    1.21
     annihilated
    1.20
    llium
    1.19
     ornamentation
    1.17
     striées
    1.17
    POSITIVE LOGITS
    oc
    1.40
    pl
    1.34
    ela
    1.30
    ock
    1.28
    ure
    1.21
    κ
    1.15
    oot
    1.15
     pour
    1.14
    cinas
    1.11
     nicht
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.