© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145270
    Prev
    Next
    INDEX
    Explanations

    die, standardize, todays, Techn

    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_0_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
    ल
    1.68
    いた
    1.45
    ne
    1.34
    ू
    1.20
    んと
    1.17
    nea
    1.15
    𝔰
    1.14
    რება
    1.12
    ル
    1.12
    ർ
    1.12
    POSITIVE LOGITS
    ت
    1.99
    a
    1.73
     It
    1.45
    y
    1.37
    0
    1.36
    ется
    1.32
     for
    1.30
    িক
    1.30
    >
    1.30
    تهم
    1.30
    Activations Density 0.000%

    No Known Activations