© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91198
    Prev
    Next
    INDEX
    Explanations

    android developer topics

    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_11_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
     or
    0.53
    rom
    0.49
    립
    0.48
    オー
    0.46
    igis
    0.45
     ou
    0.44
    _
    0.44
    issati
    0.43
    agens
    0.43
     dans
    0.43
    POSITIVE LOGITS
     задума
    0.51
    蠶
    0.47
     pensado
    0.47
     decidido
    0.46
    空调
    0.43
     মধ্যকার
    0.43
     сторона
    0.42
    го
    0.42
    暫
    0.42
    ᅠ
    0.41
    Activations Density 0.045%

    No Known Activations