© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4804
    Prev
    Next
    INDEX
    Explanations

    words related to interior spaces or furniture

    oai_token-act-pair · gemini-2.0-flash

    furniture and kitchen

    np_max-act-logits · gemini-2.0-flash

    table

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     OFDb
    -0.71
    styleType
    -0.67
     beginnetje
    -0.66
    RTEX
    -0.65
    MessageOf
    -0.63
    MemoryWarning
    -0.61
    ftagPool
    -0.59
    sproz
    -0.59
    клопе
    -0.56
    igshid
    -0.56
    POSITIVE LOGITS
     draw
    0.50
    Према
    0.48
     A
    0.48
     draws
    0.46
    ret
    0.46
    thenReturn
    0.44
     lampada
    0.43
    arias
    0.42
    rett
    0.42
    سیون
    0.42
    Activations Density 4.308%

    No Known Activations