© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77746
    Prev
    Next
    INDEX
    Explanations

    training prompts

    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_53_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
    Hor
    0.22
    WIDE
    0.21
    Hil
    0.20
     HOR
    0.20
    RANGE
    0.20
    ่ะ
    0.19
    ཝ
    0.18
     ઘટ
    0.18
    
    0.18
    覧
    0.18
    POSITIVE LOGITS
     강화
    0.23
     Mur
    0.23
    ]!=
    0.22
     Chateau
    0.22
     Qd
    0.21
    ică
    0.21
    ſe
    0.21
     armchair
    0.21
    硋
    0.21
    ](/
    0.21
    Activations Density 0.002%

    No Known Activations