© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1423
    Prev
    Next
    INDEX
    Explanations

    words associated with providing aid or assistance and also some color words.

    oai_token-act-pair · gemini-2.0-flash

    band

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     band
    -3.20
     Band
    -2.92
    band
    -2.89
    Band
    -2.86
     bands
    -2.78
     BAND
    -2.75
    BAND
    -2.63
     Bands
    -2.59
    bands
    -2.44
    Bands
    -2.39
    POSITIVE LOGITS
    TestMethod
    0.58
     оригіналу
    0.54
     Acker
    0.54
     ProtoMessage
    0.54
     snippetHide
    0.53
     XCTest
    0.49
    XMLSchema
    0.49
    μφωνα
    0.48
     biografias
    0.48
    jupiter
    0.48
    Activations Density 2.380%

    No Known Activations