© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 111
    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_12_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
     bend
    0.30
     snaps
    0.28
     télécharger
    0.27
     viewers
    0.26
     bends
    0.26
     download
    0.25
     hats
    0.25
    安
    0.24
     regulators
    0.24
    下载
    0.24
    POSITIVE LOGITS
     gemäß
    0.31
     großes
    0.31
    OOOO
    0.30
     ಸ್ವಲ್ಪ
    0.30
     großen
    0.30
     merkezi
    0.30
     mantenimiento
    0.30
    ோர்
    0.29
    orean
    0.29
    চলিত
    0.29
    Activations Density 0.043%

    No Known Activations