© 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. 257013
    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
     NCBI
    1.38
    ﻟ
    1.26
    ût
    1.20
     ctrl
    1.19
    ത്യ
    1.18
    образ
    1.17
    غو
    1.17
    િયલ
    1.16
    श्त
    1.15
    лим
    1.13
    POSITIVE LOGITS
                            
    1.20
     masterpieces
    1.19
    _______________
    1.17
     Encoder
    1.16
     מס
    1.16
     monotonicity
    1.16
     Fully
    1.15
    ​.
    1.13
     abnormalities
    1.12
                        
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.