© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145678
    Prev
    Next
    INDEX
    Explanations

    arrangement, arrondissement, Arrhenius

    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_0_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
     αρχ
    1.41
    ’
    1.41
    {
    1.39
    ни
    1.28
     excites
    1.22
    𝐠
    1.21
     ingresos
    1.20
     activos
    1.20
    ोन
    1.20
     ευ
    1.20
    POSITIVE LOGITS
    ne
    1.59
    8
    1.45
     I
    1.40
    ні
    1.36
    اد
    1.35
    se
    1.25
    ۔
    1.22
    al
    1.20
    7
    1.20
    ının
    1.19
    Activations Density 0.000%

    No Known Activations