© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98158
    Prev
    Next
    INDEX
    Explanations

    cannotwill notinstructionsfines

    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_14_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
    𝐨
    0.55
    𝐢
    0.54
    ңү
    0.51
     Alli
    0.51
     ይችላል
    0.50
    ｏ
    0.50
    ならない
    0.49
     Canadá
    0.49
    െടുത്തു
    0.48
    कोलॉजी
    0.48
    POSITIVE LOGITS
    :]
    0.62
    :<
    0.57
     :
    0.56
    :
    0.55
    gl
    0.54
    est
    0.53
     έναν
    0.53
    Drinking
    0.52
    ᱔
    0.52
     \
    0.50
    Activations Density 0.000%

    No Known Activations