© 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. 199593
    Prev
    Next
    INDEX
    Explanations

    prefix 'ab'

    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
    initialized
    0.37
    Initialized
    0.37
    SCOPE
    0.36
     deuterium
    0.35
    iennes
    0.35
    fry
    0.35
    棂
    0.35
    不太
    0.35
     구축
    0.35
     Fry
    0.34
    POSITIVE LOGITS
     af
    1.28
    Ab
    1.22
     Ab
    1.21
     ab
    1.20
     Af
    1.09
     av
    1.09
    Af
    1.06
     अफ
    1.05
     abge
    1.05
     аб
    1.00
    Activations Density 0.015%

    No Known Activations