© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133117
    Prev
    Next
    INDEX
    Explanations

    dander

    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_6_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
    י
    0.86
    ך
    0.84
    )
    0.81
     cure
    0.79
     newsc
    0.79
    ]
    0.77
     bilingual
    0.76
    প্যাথ
    0.75
     spore
    0.75
    защи
    0.75
    POSITIVE LOGITS
    m
    1.41
    an
    1.31
    na
    1.26
    al
    1.23
    t
    1.21
    ad
    1.15
    to
    1.09
    ni
    1.07
    l
    1.07
    ll
    1.06
    Activations Density 0.000%

    No Known Activations