© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7530
    Prev
    Next
    INDEX
    Explanations

    language regarding legal negligence or failure to fulfill duties

    oai_token-act-pair · gemini-2.0-flash

    words related to legal obligations and failures

    np_token-act-pair-logits · gpt-4o-mini

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    にほんブログ村
    -0.52
    ẠI
    -0.50
    InitStruct
    -0.48
     OMITBAD
    -0.47
    anément
    -0.47
    emplare
    -0.46
    richTextPanel
    -0.45
    }))
    -0.45
     judging
    -0.44
    Clik
    -0.44
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.60
    hexyl
    0.60
     comply
    0.59
     ttk
    0.57
    kháu
    0.57
     meet
    0.56
    thenReturn
    0.54
     disclose
    0.53
     publish
    0.53
    meet
    0.53
    Activations Density 3.926%

    No Known Activations