© 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-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120075
    Prev
    Next
    INDEX
    Explanations

    cially, importantly, crucially

    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_27_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
     significativas
    0.40
    瑕
    0.37
     minimale
    0.36
     niž
    0.35
     ਕੋ
    0.35
     fluency
    0.35
    ਗਾ
    0.35
     jangka
    0.35
     kitten
    0.34
     procedural
    0.34
    POSITIVE LOGITS
    á
    0.36
    ደረ
    0.36
     importantly
    0.35
     Importantly
    0.35
     wisely
    0.35
     honourable
    0.34
    Sept
    0.34
    tanggal
    0.33
    ?”.
    0.33
    baru
    0.32
    Activations Density 0.003%

    No Known Activations