© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59065
    Prev
    Next
    INDEX
    Explanations

    thinly veiled or sliced

    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_2_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
    1
    1.49
    д
    1.37
    یت
    1.20
    й
    1.20
    ма
    1.18
     étaient
    1.18
     amplio
    1.15
    где
    1.14
    あ
    1.14
    ৩
    1.13
    POSITIVE LOGITS
    ana
    1.31
    h
    1.30
    x
    1.30
    ons
    1.16
    f
    1.16
    re
    1.13
    z
    1.11
    ag
    1.08
    el
    1.04
    ah
    1.03
    Activations Density 0.000%

    No Known Activations