© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15987
    Prev
    Next
    INDEX
    Explanations

    instances of requests for assistance

    oai_token-act-pair · gemini-2.0-flash

    help requests

    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
     tartalomajánló
    -0.64
    migrationBuilder
    -0.59
    ьа
    -0.57
     endforeach
    -0.53
    VertexAttrib
    -0.51
     defStyleAttr
    -0.51
    RegressionTest
    -0.50
     Urqu
    -0.50
    Okey
    -0.50
    cvtColor
    -0.49
    POSITIVE LOGITS
     linkovi
    0.52
     amt
    0.50
    athie
    0.49
     Halter
    0.47
     Namur
    0.47
    RUnlock
    0.46
    entor
    0.45
     nid
    0.45
    ensburg
    0.44
    ávajú
    0.44
    Activations Density 11.595%

    No Known Activations