© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14654
    Prev
    Next
    INDEX
    Explanations

    temperature values

    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_34_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
    हित्य
    0.32
    IMENTO
    0.31
    ahasan
    0.30
    roller
    0.30
    <unused56>
    0.29
    erek
    0.29
    yama
    0.29
    Cement
    0.29
    ოველ
    0.29
     roller
    0.28
    POSITIVE LOGITS
     sortie
    0.36
    arche
    0.34
     intégral
    0.32
     Дей
    0.32
     Vessels
    0.30
     drink
    0.30
     reformation
    0.30
     большинства
    0.29
     (=
    0.29
     کیل
    0.29
    Activations Density 0.016%

    No Known Activations