© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9135
    Prev
    Next
    INDEX
    Explanations

    0.btc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ﻱ
    2.08
    ﺓ
    2.04
    ⮚
    1.92
     바로
    1.92
    𝒓
    1.90
     plurality
    1.87
    ים
    1.83
     RBI
    1.81
    ﻩ
    1.80
     FGD
    1.79
    POSITIVE LOGITS
    it
    2.11
    ر
    2.08
    ﻪ
    1.98
     conson
    1.84
    er
    1.83
     zamanda
    1.82
    ح
    1.81
    jest
    1.80
    ு
    1.80
    ч
    1.78
    Activations Density 0.027%

    No Known Activations