© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 77787
    Prev
    Next
    INDEX
    Explanations

    rely on, rely solely on

    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_31_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
     pointless
    0.39
    IdleSync
    0.38
     nothing
    0.38
     administrativos
    0.38
    君
    0.37
     vorticity
    0.37
    admins
    0.37
    nothing
    0.36
    োয়
    0.36
    Give
    0.36
    POSITIVE LOGITS
     Columns
    0.45
     аре
    0.43
     তুলনায়
    0.40
     SSE
    0.39
    खन
    0.39
     হ্রাস
    0.39
    akis
    0.39
    ட்ரா
    0.38
    thione
    0.38
    搽
    0.38
    Activations Density 0.003%

    No Known Activations