© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198202
    Prev
    Next
    INDEX
    Explanations

    fulfill requests

    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_46_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
    Hammer
    0.44
    hammer
    0.42
     Hammer
    0.41
    शूट
    0.41
    ><?
    0.40
    فرج
    0.40
     hammer
    0.38
    稹
    0.37
    橛
    0.37
    mack
    0.36
    POSITIVE LOGITS
     Bianco
    0.42
    ಕೋ
    0.40
    ითხ
    0.39
     cors
    0.38
     resc
    0.38
     infos
    0.37
    coil
    0.37
     eyeing
    0.36
     ಅಗ
    0.36
    quent
    0.35
    Activations Density 0.000%

    No Known Activations