© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261155
    Prev
    Next
    INDEX
    Explanations

    case singular

    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_5_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
    ל
    1.20
    א
    1.13
    ﻴ
    1.13
    на
    1.10
    子の
    1.09
    لي
    1.08
     laboratoire
    1.06
     hidrógeno
    1.05
    のカ
    1.03
    の見
    1.02
    POSITIVE LOGITS
     be
    1.47
     as
    1.34
    ↵↵
    1.17
     are
    1.05
    Y
    1.01
    ur
    1.00
    M
    0.99
    E
    0.99
    ু
    0.98
    F
    0.98
    Activations Density 0.000%

    No Known Activations