© 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. 2446
    Prev
    Next
    INDEX
    Explanations

    various forms of "have", "has" and "had"

    oai_token-act-pair · gemini-2.0-flash

    negation

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

    variants of "no"

    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
    Abitanti
    -0.57
    enya
    -0.53
    tanleria
    -0.52
    청
    -0.51
    })()
    -0.50
    ISSE
    -0.48
    occa
    -0.47
    Jîn
    -0.46
    CONSIN
    -0.45
    galus
    -0.45
    POSITIVE LOGITS
     no
    2.88
    no
    2.06
     NO
    1.77
    No
    1.68
     No
    1.59
    NO
    1.50
     keine
    1.20
     nessun
    1.19
     keinen
    1.17
     kein
    1.14
    Activations Density 2.097%

    No Known Activations