© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31579
    Prev
    Next
    INDEX
    Explanations

    chat moderation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     bat
    0.51
     J
    0.48
     bats
    0.43
     batting
    0.41
    ității
    0.41
     Bat
    0.41
     dong
    0.40
     dox
    0.40
    bat
    0.39
     Joey
    0.39
    POSITIVE LOGITS
    ရေ
    0.42
    髂
    0.40
    oS
    0.40
    Pin
    0.40
     الز
    0.39
     отме
    0.39
    Aloe
    0.38
    Cos
    0.38
    пин
    0.38
     యా
    0.38
    Activations Density 0.001%

    No Known Activations