© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160398
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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_2_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
    )
    1.43
    cą
    1.34
    cott
    1.29
    "
    1.20
    }
    1.20
    cı
    1.16
    ные
    1.11
    の
    1.09
    cji
    1.07
    casa
    1.07
    POSITIVE LOGITS
    ר
    1.46
    s
    1.38
    er
    1.35
    र
    1.28
     to
    1.27
    te
    1.25
     for
    1.20
    t
    1.13
    ن
    1.10
     revelations
    1.07
    Activations Density 0.000%

    No Known Activations