© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163914
    Prev
    Next
    INDEX
    Explanations

    register your

    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_13_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
    
    0.63
    ’
    0.61
    d
    0.61
    7
    0.59
    <0x0D>
    0.57
    ’,
    0.56
    ’?
    0.54
     d
    0.54
     grey
    0.54
     matchup
    0.51
    POSITIVE LOGITS
     токси
    0.57
     کہا
    0.56
     يقول
    0.56
    ally
    0.55
     কথাবার
    0.55
    РИ
    0.54
    აც
    0.53
    Ⲏ
    0.53
     заяви
    0.53
     الموس
    0.53
    Activations Density 0.001%

    No Known Activations