© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159474
    Prev
    Next
    INDEX
    Explanations

    斯, e, ex, R, ur followed by Chinese or English words

    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_2_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
     shortcomings
    1.35
    نی
    1.32
    دی
    1.27
    ش
    1.27
    सी
    1.25
    ן
    1.20
     offrir
    1.17
     impulso
    1.17
    می
    1.14
     aiuto
    1.14
    POSITIVE LOGITS
     be
    1.91
    been
    1.44
     been
    1.40
    }
    1.36
    '
    1.31
     can
    1.29
     have
    1.27
    be
    1.23
    á
    1.21
    {
    1.20
    Activations Density 0.001%

    No Known Activations