© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 110206
    Prev
    Next
    INDEX
    Explanations

    prohibitively + expensive/slow/high/long

    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
    in
    2.02
    ك
    1.59
    其他
    1.45
    and
    1.42
    as
    1.33
    an
    1.32
    ip
    1.32
    هم
    1.24
    were
    1.20
    u
    1.18
    POSITIVE LOGITS
    <0x80>
    1.15
    ד
    1.14
    (
    1.11
     effusion
    1.08
    お店
    1.05
    )
    1.03
    ることが
    1.00
    {
    1.00
     لیکن
    0.98
     infarction
    0.98
    Activations Density 0.001%

    No Known Activations