© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133620
    Prev
    Next
    INDEX
    Explanations

    -er suffix

    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_50_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
    utherland
    0.42
     Butcher
    0.41
    太平
    0.40
    ITAS
    0.40
    <0x9F>
    0.39
    itas
    0.39
    icone
    0.39
    𝒚
    0.39
    ISES
    0.38
    consistency
    0.37
    POSITIVE LOGITS
    ers
    0.90
    erc
    0.87
    erg
    0.85
    er
    0.79
    ER
    0.76
    erd
    0.76
    ер
    0.74
    erm
    0.71
    erset
    0.70
    ERG
    0.70
    Activations Density 0.001%

    No Known Activations