© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7212
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing uncertainty or tentativeness through negation, qualification, or hedging.

    oai_token-act-pair · gemini-2.0-flash

    negation of all

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    all
    -0.52
     all
    -0.47
    वरण
    -0.45
    entire
    -0.44
    himura
    -0.44
     hết
    -0.44
    čan
    -0.40
     note
    -0.40
    Dura
    -0.40
     باخ
    -0.38
    POSITIVE LOGITS
     raiſ
    0.77
     Reſ
    0.74
     poffible
    0.71
     neceff
    0.71
     neceffary
    0.68
     caufe
    0.68
    rungsseite
    0.68
     cauſe
    0.67
     houſe
    0.67
     Houſe
    0.66
    Activations Density 32.409%

    No Known Activations