© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241183
    Prev
    Next
    INDEX
    Explanations

    back door

    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_25_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
    胍
    0.43
     multipliers
    0.42
     sacram
    0.41
    DEF
    0.40
     desem
    0.39
     preservatives
    0.38
     contraceptives
    0.38
     cultura
    0.38
     multiplication
    0.38
    лым
    0.37
    POSITIVE LOGITS
     Bole
    0.37
    anka
    0.37
    禾
    0.36
    вається
    0.36
     अत्या
    0.36
     акаде
    0.34
     Painter
    0.34
    rosse
    0.33
    õ
    0.33
     Где
    0.32
    Activations Density 0.001%

    No Known Activations