© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258489
    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
    ामध्ये
    1.24
    bote
    1.17
     legge
    1.16
     hona
    1.15
     Tä
    1.15
    TUB
    1.15
    宋
    1.14
    ن
    1.13
    sr
    1.12
     Jeg
    1.09
    POSITIVE LOGITS
     foreseeable
    1.22
    слов
    1.16
    नी
    1.10
     accelerated
    1.10
    yank
    1.09
     volts
    1.05
     tová
    1.03
     específicamente
    1.03
     retaliation
    1.02
     arrhythmias
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.