© 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. 14712
    Prev
    Next
    INDEX
    Explanations

    the word "however" and words near it

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "however"

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

    however

    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
     дописавши
    -1.34
    RenderAtEndOf
    -1.33
     تضيفلها
    -1.26
     виправивши
    -1.24
    featureID
    -1.20
     GenerationType
    -1.16
     typelib
    -1.15
     فريبيس
    -1.13
     jScrollPane
    -1.13
    expandindo
    -1.09
    POSITIVE LOGITS
    ?
    0.56
    ]
    0.53
    ><!--
    0.52
    ![
    0.50
    }
    0.49
    <eos>
    0.48
    !
    0.47
    ’
    0.47
    )
    0.46
    ご
    0.46
    Activations Density 1.502%

    No Known Activations