© 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. 159557
    Prev
    Next
    INDEX
    Explanations

    input parameter or variable

    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
    the
    1.30
    and
    1.03
    ні
    1.02
    un
    1.02
    اب
    1.02
    a
    1.00
     როგორც
    1.00
    ە
    1.00
    ка
    0.98
    engkap
    0.97
    POSITIVE LOGITS
    ’
    1.85
    '
    1.69
    \
    1.40
    ות
    1.38
     was
    1.30
     to
    1.25
    ס
    1.13
     at
    1.11
    AK
    1.08
    n
    1.06
    Activations Density 0.008%

    No Known Activations