© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67462
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    冷凍
    0.42
    )=(\
    0.40
    утбу
    0.40
    čnog
    0.39
    }+(\
    0.39
    artig
    0.38
    =(\
    0.38
    óa
    0.37
    ))(
    0.37
    積分
    0.37
    POSITIVE LOGITS
    Experience
    0.49
    experience
    0.47
     Experience
    0.47
     smells
    0.46
     stars
    0.46
     experiencia
    0.46
     experience
    0.45
    Stars
    0.44
     majesty
    0.44
     تجربه
    0.44
    Activations Density 0.117%

    No Known Activations