© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13105
    Prev
    Next
    INDEX
    Explanations

    the prefix "non-"

    oai_token-act-pair · gemini-2.0-flash

    non

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -0.78
    rungsseite
    -0.68
    uxxxx
    -0.68
    Parcelize
    -0.66
    abstractmethod
    -0.66
     الحره
    -0.65
     समीक्षाओं
    -0.65
    SequentialGroup
    -0.63
     שוליים
    -0.63
    ⓘ
    -0.62
    POSITIVE LOGITS
    ta
    0.50
    mat
    0.47
    a
    0.44
    ral
    0.42
    ัว
    0.42
     parabolic
    0.41
    PhysRevLett
    0.41
     Omer
    0.40
    tech
    0.40
    nar
    0.40
    Activations Density 1.430%

    No Known Activations