© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201330
    Prev
    Next
    INDEX
    Explanations

    starting again

    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_12_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
    те
    0.62
    </h2>
    0.60
    MQTT
    0.60
    тан
    0.59
    Owner
    0.57
    NCC
    0.57
    ChooseServer
    0.56
    ﻜ
    0.56
     owner
    0.55
     एनसी
    0.55
    POSITIVE LOGITS
     Ital
    0.63
     Yugoslavia
    0.56
    ür
    0.54
     Lemma
    0.54
     cabelo
    0.54
     cabello
    0.53
     daarna
    0.52
     cinereo
    0.52
    ä
    0.50
    ና
    0.50
    Activations Density 0.000%

    No Known Activations