© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42197
    Prev
    Next
    INDEX
    Explanations

    greenhouse effect

    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_3_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
    ালার
    0.60
    ước
    0.60
    と呼ば
    0.58
    锜
    0.57
    取締役
    0.54
    <unused2130>
    0.54
    𝟎
    0.53
    <0x9C>
    0.53
     periódico
    0.53
     Христос
    0.53
    POSITIVE LOGITS
    in
    1.00
    ي
    0.82
    "
    0.81
    ’
    0.74
    י
    0.68
    i
    0.68
    ম
    0.67
    3
    0.66
    e
    0.65
    fight
    0.65
    Activations Density 0.006%

    No Known Activations