© 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. 133058
    Prev
    Next
    INDEX
    Explanations

    gentle followed by nature words

    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
     as
    1.34
    </h2>
    1.32
    lt
    1.31
    ة
    1.26
    r
    1.23
    il
    1.20
    ut
    1.19
    <0x0D>
    1.18
     Ал
    1.17
    nt
    1.16
    POSITIVE LOGITS
     wolf
    0.97
     tariff
    0.96
     marshmallow
    0.91
     deluge
    0.90
     groan
    0.90
    <0x86>
    0.87
     gallon
    0.87
     minivan
    0.86
     velvet
    0.86
     mortar
    0.86
    Activations Density 0.004%

    No Known Activations