© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16415
    Prev
    Next
    INDEX
    Explanations

    predicting likelihood

    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_40_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
    ﻅ
    0.41
    লী
    0.40
    лари
    0.40
     Beginn
    0.38
     మ్యాచ్
    0.37
    𝜇
    0.36
     Làm
    0.36
    فر
    0.35
    믿
    0.35
    欲
    0.35
    POSITIVE LOGITS
    likely
    0.40
     likely
    0.39
    ⑵
    0.38
    ickness
    0.37
    elihood
    0.36
    िएको
    0.36
    inesis
    0.35
    ştur
    0.35
    ிறார்
    0.35
    iewicz
    0.34
    Activations Density 0.020%

    No Known Activations