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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 165425
    Prev
    Next
    INDEX
    Explanations

    **correlations between words**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
    ותו
    0.39
    Ꮘ
    0.37
    émy
    0.36
    Smooth
    0.35
    წვ
    0.35
    今後の
    0.35
     canalicul
    0.34
    zyła
    0.34
    本作
    0.33
    ນະ
    0.33
    POSITIVE LOGITS
    ionat
    0.36
    -\
    0.35
     conscient
    0.35
     Cots
    0.34
    olo
    0.33
     Chateau
    0.33
     Jon
    0.33
     Ö
    0.33
     Downtown
    0.33
     Bosch
    0.33
    Activations Density 0.033%

    No Known Activations