© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146203
    Prev
    Next
    INDEX
    Explanations

    financing

    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
    f
    1.89
    a
    1.84
    1
    1.52
    lar
    1.40
    were
    1.36
    ol
    1.35
    া
    1.30
    ar
    1.25
    ه
    1.23
    with
    1.21
    POSITIVE LOGITS
    IS
    1.33
    জ
    1.24
     jeopard
    1.23
     sharpen
    1.17
    ೇವಿನ
    1.17
     なかっ
    1.16
    나
    1.16
    Ⴎ
    1.15
     sacrificing
    1.13
    陘
    1.13
    Activations Density 0.000%

    No Known Activations