© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3847
    Prev
    Next
    INDEX
    Explanations

    holding objects

    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_39_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
    浴室
    0.37
    contenido
    0.37
    戦
    0.37
     (($
    0.36
    ειο
    0.36
    еро
    0.35
    盯
    0.35
    oraj
    0.35
    内容的
    0.35
     пунк
    0.34
    POSITIVE LOGITS
     paintbrush
    0.79
     knife
    0.79
    刀
    0.74
     laptop
    0.73
     microphone
    0.73
     briefcase
    0.71
     clipboard
    0.70
     Knife
    0.69
     flashlight
    0.68
     handgun
    0.68
    Activations Density 0.077%

    No Known Activations