© 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. 13279
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to negative assertions and disagreements in dialogue

    oai_token-act-pair · gemini-2.0-flash

    subjective evaluations

    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
     esternos
    -0.50
     Administrativna
    -0.48
     فريبيس
    -0.47
    getMenuInflater
    -0.46
     postIndex
    -0.45
    Inter
    -0.42
    ếp
    -0.41
    tamientos
    -0.41
     रि
    -0.40
    　→
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    0.67
    ">//
    0.66
     виправивши
    0.64
    gbaar
    0.60
    ConfigureAwait
    0.60
     bezeichneter
    0.59
     varargin
    0.59
    artifactId
    0.58
     iſt
    0.56
    BrowserModule
    0.56
    Activations Density 4.118%

    No Known Activations