© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110761
    Prev
    Next
    INDEX
    Explanations

    detrimental observation or consequence

    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
    లో
    1.12
    l
    1.12
    D
    1.12
    of
    1.11
    B
    1.11
    K
    1.09
    th
    1.08
    C
    1.04
    T
    1.02
    N
    1.00
    POSITIVE LOGITS
     are
    1.43
     as
    1.41
    ุ
    1.40
    {
    1.27
    да
    1.20
    ओं
    1.19
    ;
    1.15
    ের
    1.13
     ecz
    1.12
    ی
    1.12
    Activations Density 0.000%

    No Known Activations