© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33036
    Prev
    Next
    INDEX
    Explanations

    each

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     keduanya
    0.60
     begge
    0.58
     ambas
    0.54
    两者
    0.52
     둘
    0.52
     entrambe
    0.51
     ambos
    0.50
     دونوں
    0.48
     entrambi
    0.48
    둘
    0.48
    POSITIVE LOGITS
     each
    3.34
    each
    2.88
    Each
    2.83
     Each
    2.81
     EACH
    2.63
    แต่ละ
    2.39
     hver
    2.36
     каждого
    2.31
     प्रत्येक
    2.28
     fiecare
    2.27
    Activations Density 0.614%

    No Known Activations