© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3643
    Prev
    Next
    INDEX
    Explanations

    references to the word "planet"

    oai_token-act-pair · gemini-2.0-flash

    planet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.70
     Nor
    -0.59
     the
    -0.59
     la
    -0.56
     Ver
    -0.56
    ely
    -0.55
     My
    -0.54
     For
    -0.54
     Our
    -0.53
     fact
    -0.53
    POSITIVE LOGITS
     myſelf
    1.13
     Efq
    1.13
     Majefty
    1.09
     pleaſure
    1.00
     fhort
    0.99
     itſelf
    0.96
    .",
    0.96
     Houſe
    0.96
    ^(@)
    0.94
    extAlignment
    0.94
    Activations Density 1.081%

    No Known Activations