© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229925
    Prev
    Next
    INDEX
    Explanations

    what is followed by is are happens

    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_6_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
    .
    0.98
    +
    0.92
    iv
    0.91
    ertation
    0.89
    irectional
    0.88
    aur
    0.85
    iding
    0.82
    apport
    0.81
    oting
    0.81
    ested
    0.81
    POSITIVE LOGITS
    л
    1.62
    ים
    1.32
    ی
    1.18
    s
    1.16
    ل
    1.14
    ک
    1.14
    ש
    1.12
    те
    1.06
    ז
    1.05
    τι
    1.03
    Activations Density 0.006%

    No Known Activations