© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124624
    Prev
    Next
    INDEX
    Explanations

    Genghis Khan or ketene lamp

    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_3_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
    }=
    0.83
    𝘀
    0.81
    К
    0.74
    ч
    0.73
    კ
    0.72
    ದಲ್ಲಿ
    0.72
    কে
    0.71
    }>
    0.71
    في
    0.71
    }/>
    0.71
    POSITIVE LOGITS
    I
    0.96
    ong
    0.89
     can
    0.77
    ä
    0.76
     It
    0.73
     don
    0.71
    ain
    0.70
    ang
    0.66
     You
    0.66
     haven
    0.66
    Activations Density 0.000%

    No Known Activations