© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12464
    Prev
    Next
    INDEX
    Explanations

    the token "tor", which often appears as part of the word "torsional" or "torrefaction"

    oai_token-act-pair · gemini-2.0-flash

    tokens related to "tor" or "Tors."

    np_token-act-pair-logits · gpt-4o-mini

    torsion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     <<<<<<<<<<<<<<
    -0.57
    ніципа
    -0.56
    cshtml
    -0.55
    ombic
    -0.54
    gnan
    -0.53
    SerializedName
    -0.52
     ویکی‌پدی
    -0.52
     every
    -0.50
    ])[
    -0.50
     Every
    -0.49
    POSITIVE LOGITS
     NSError
    0.50
     IndexPath
    0.48
    Mhz
    0.45
    umpad
    0.45
    UIButton
    0.44
    usermodel
    0.44
     fiables
    0.44
    rense
    0.42
     disait
    0.42
     préc
    0.41
    Activations Density 0.270%

    No Known Activations