© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 4555
    Prev
    Next
    INDEX
    Explanations

    mentions of days of the week, or related words like 'year', 'night', 'afternoon', combined with possible keywords like 'authorities', 'fires', "lines"

    oai_token-act-pair · gemini-2.0-flash

    days of the week

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SourceChecksum
    -0.67
    ]")]
    -0.65
    findpost
    -0.60
    ')";
    -0.54
    #+#
    -0.54
     SUNDAY
    -0.53
    TagMode
    -0.53
     endforeach
    -0.53
    CloseOperation
    -0.51
    ̍t
    -0.49
    POSITIVE LOGITS
     estekak
    0.63
     arrivant
    0.56
    ida
    0.56
     crum
    0.51
     Jank
    0.50
    luft
    0.49
    focusable
    0.48
    idable
    0.48
     Ram
    0.48
    Embeddable
    0.48
    Activations Density 2.640%

    No Known Activations