© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167102
    Prev
    Next
    INDEX
    Explanations

    environment activation commands

    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_34_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
     notched
    0.40
    ⩾
    0.38
    kits
    0.38
     &[
    0.37
    ન્ટે
    0.37
     Created
    0.37
     Grading
    0.37
    véd
    0.36
     જા
    0.35
     pasal
    0.35
    POSITIVE LOGITS
     refugee
    0.42
     obedient
    0.42
     refugees
    0.41
     obeys
    0.40
     Refugees
    0.38
     attitudes
    0.37
     obedience
    0.37
    颖
    0.36
    unes
    0.36
     लाभार्थियों
    0.36
    Activations Density 0.002%

    No Known Activations