© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2063
    Prev
    Next
    INDEX
    Explanations

    references to proximity and location

    oai_token-act-pair · gemini-2.0-flash

    Describing placement or position

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     right
    -1.12
    right
    -1.02
     Right
    -1.01
    Right
    -1.00
    RIGHT
    -0.86
     RIGHT
    -0.86
     kasarigan
    -0.82
    UIControlState
    -0.77
     右
    -0.77
    右
    -0.77
    POSITIVE LOGITS
     to
    0.68
    ̓
    0.47
    ront
    0.46
    のだろう
    0.43
     glutton
    0.43
    ULATION
    0.43
    ruzione
    0.42
    juli
    0.42
    jne
    0.41
     dû
    0.41
    Activations Density 1.952%

    No Known Activations