© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171078
    Prev
    Next
    INDEX
    Explanations

    but discouraging harmful actions

    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_20_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
    ProductRunnable
    0.27
    (\|\
    0.27
    рсә
    0.27
    Votre
    0.26
     ransom
    0.26
    マーケ
    0.25
    需
    0.25
    ("__
    0.25
     instalment
    0.25
    inė
    0.25
    POSITIVE LOGITS
     Instead
    0.33
    ter
    0.29
    instead
    0.28
     instead
    0.28
    2
    0.28
    EN
    0.28
    sc
    0.27
    grad
    0.27
     दीपक
    0.27
     EN
    0.27
    Activations Density 0.005%

    No Known Activations