© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87996
    Prev
    Next
    INDEX
    Explanations

    structure or time period

    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_3_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
    nél
    1.03
    n
    0.91
    िंग
    0.82
    बर्ग
    0.77
    nál
    0.76
    nání
    0.71
    ing
    0.69
    cambrian
    0.67
    hwar
    0.65
    κρα
    0.64
    POSITIVE LOGITS
    3
    0.77
    4
    0.67
    Ob
    0.64
    েয়
    0.64
    /;
    0.62
    ২০
    0.61
    ం
    0.61
    for
    0.60
    FIRST
    0.59
    rechte
    0.59
    Activations Density 0.016%

    No Known Activations