© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212981
    Prev
    Next
    INDEX
    Explanations

    Ollama and llama.cpp for running LLMs

    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_5_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
    is
    1.41
    اری
    1.36
    ină
    1.29
    ки
    1.21
    t
    1.16
    시
    1.16
    υτό
    1.14
    ύ
    1.14
    on
    1.13
    ли
    1.11
    POSITIVE LOGITS
     Have
    1.20
    ד
    1.17
     Bar
    1.16
    }\
    1.16
     o
    1.13
     Jeden
    1.12
     Jam
    1.10
     Able
    1.09
     Don
    1.09
    الك
    1.09
    Activations Density 0.000%

    No Known Activations