© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12228
    Prev
    Next
    INDEX
    Explanations

    the word "right" and also activates on mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    right

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     dia
    -0.45
     existing
    -0.42
     maaf
    -0.41
     anh
    -0.40
    <!
    -0.39
    ")]
    -0.39
    ))]
    -0.38
    </h5>
    -0.38
     couple
    -0.37
     stad
    -0.36
    POSITIVE LOGITS
    _{\
    1.09
    _{
    1.06
    ^{
    1.00
    ^(@)
    0.98
    ^{\
    0.98
    }_{\
    0.97
    ^{-
    0.95
    ^{+
    0.93
    }_{
    0.91
    ^{(
    0.91
    Activations Density 0.554%

    No Known Activations