© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3415
    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_2_width_16k_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
    е
    3.13
    й
    2.81
    ి
    2.52
    ه
    2.49
    ably
    2.41
    acją
    2.33
    你要
    2.31
    ulence
    2.30
    िक
    2.21
    י
    2.19
    POSITIVE LOGITS
     beetje
    3.11
     Mesmo
    2.88
     fibrils
    2.86
    տր
    2.85
    那时候
    2.76
    𝑆
    2.75
    ﻤ
    2.75
     diastere
    2.75
    ти
    2.74
    𝑘
    2.74
    Activations Density 0.026%

    No Known Activations