© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58221
    Prev
    Next
    INDEX
    Explanations

    Micro

    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_59_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
     little
    0.55
    little
    0.49
     LITTLE
    0.47
     صغير
    0.46
     maž
    0.45
     малень
    0.45
     poco
    0.44
    小
    0.44
     мало
    0.43
     diminutive
    0.43
    POSITIVE LOGITS
    studded
    0.53
     Act
    0.48
    Act
    0.47
    fries
    0.46
     act
    0.44
    rice
    0.44
    filled
    0.43
    frying
    0.43
     akt
    0.42
    वेश
    0.41
    Activations Density 0.001%

    No Known Activations