© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244870
    Prev
    Next
    INDEX
    Explanations

    punctuation, separators, list items, special tokens

    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_40_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
    icron
    0.38
    crits
    0.37
    henius
    0.37
     meditations
    0.37
    CTS
    0.36
    ल्लभ
    0.35
    ragen
    0.35
    暖
    0.34
     देन
    0.34
    iche
    0.34
    POSITIVE LOGITS
    itimate
    0.43
     Purchase
    0.42
     포함
    0.37
     -*-
    0.37
     reinforcements
    0.37
    第二百
    0.36
    成績
    0.36
    Duty
    0.36
     బోర్
    0.36
     Rein
    0.36
    Activations Density 0.000%

    No Known Activations