© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15409
    Prev
    Next
    INDEX
    Explanations

    the words "it", "to", "come", "does" and "when".

    oai_token-act-pair · gemini-2.0-flash

    argumentsReason: broad theme from top activating texts.arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     come
    -2.52
     comes
    -2.48
     Come
    -2.41
     Comes
    -2.38
    Come
    -2.34
    Comes
    -2.23
    come
    -2.22
    comes
    -2.20
     COME
    -2.20
     coming
    -2.16
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
    PDOException
    0.59
    Datuak
    0.53
    DataAnnotations
    0.50
    YLON
    0.49
    GMENT
    0.49
    tibles
    0.48
    weis
    0.47
    findpost
    0.47
    })}\
    0.47
    Activations Density 2.308%

    No Known Activations