© 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. 576
    Prev
    Next
    INDEX
    Explanations

    security related terms and phrases

    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
     patron
    0.40
    <{},
    0.39
     exact
    0.38
     ګرځنده
    0.38
     Patron
    0.38
     hinter
    0.37
     haplotype
    0.37
    :'],
    0.37
    ोंग
    0.36
     patronage
    0.36
    POSITIVE LOGITS
    Casey
    0.42
    omeg
    0.40
    crystalline
    0.37
    !='')
    0.36
    ┓
    0.36
    Burst
    0.35
    鸞
    0.35
    Autow
    0.35
     सप्ताह
    0.35
    nate
    0.34
    Activations Density 0.014%

    No Known Activations