© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8158
    Prev
    Next
    INDEX
    Explanations

    the contraction "I've" and some of the words around it

    oai_token-act-pair · gemini-2.0-flash

    negative phrases or expressions of denial

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

    ve

    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
     chi̍t
    -0.94
    Viitteet
    -0.81
     виправивши
    -0.80
    دانشنامهٔ
    -0.76
    StoryboardSegue
    -0.76
    Искәрмәләр
    -0.75
    DOCTYPE
    -0.72
     OMITBAD
    -0.72
    providedIn
    -0.71
    InjectAttribute
    -0.70
    POSITIVE LOGITS
     no
    0.61
     not
    0.59
     never
    0.53
     rarement
    0.49
     seen
    0.49
     develops
    0.47
     spends
    0.46
     quedado
    0.46
     nooit
    0.45
     had
    0.45
    Activations Density 0.789%

    No Known Activations