Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261349
    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
    দের
    1.20
    й
    1.12
    ே
    1.10
    위
    1.07
    ביל
    1.03
    რა
    1.02
    fwlink
    1.02
    ప్పుడు
    1.01
    Quem
    1.00
    在
    0.99
    POSITIVE LOGITS
     Lots
    1.18
    ERS
    1.11
     lors
    1.10
     Automobiles
    1.09
    귿
    1.09
    یاں
    1.08
    ECC
    1.06
    ELTS
    1.06
    ungere
    1.04
    ﻥ
    1.04
    Activations Density 0.000%

    No Known Activations