© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195684
    Prev
    Next
    INDEX
    Explanations

    possessive particles and interjections

    np_acts-logits-general · gemini-2.5-flash-lite

    technical and code

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    phrases that describe technical instructions or concepts, especially related to cybersecurity and language translation.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    nya
    0.26
    ні
    0.26
    지
    0.26
    ный
    0.24
    ‌است
    0.24
    তে
    0.24
    ные
    0.24
    amento
    0.22
    ных
    0.22
    ق
    0.21
    POSITIVE LOGITS
    he
    0.23
    B
    0.23
     Input
    0.22
     with
    0.22
    N
    0.22
     It
    0.22
    0
    0.21
     to
    0.21
     If
    0.21
     Editor
    0.21
    Activations Density 0.010%

    No Known Activations