© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86626
    Prev
    Next
    INDEX
    Explanations

    pronouns like he, they, their

    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_23_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
    телем
    0.44
     مبلغ
    0.42
    珍珠
    0.41
     المبلغ
    0.41
    ECH
    0.40
    彥
    0.40
    の開発
    0.40
    䒨
    0.40
     CPP
    0.40
    劧
    0.40
    POSITIVE LOGITS
    atomic
    0.43
    ាត
    0.42
    issa
    0.39
    unto
    0.38
    stats
    0.37
    Atomic
    0.37
    anty
    0.37
    aid
    0.36
    ALL
    0.36
    rig
    0.36
    Activations Density 0.000%

    No Known Activations