© 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. 9513
    Prev
    Next
    INDEX
    Explanations

    the word "feedback" and phrases related to opinions

    oai_token-act-pair · gemini-2.0-flash

    feedback

    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
    ]")]
    -1.07
    tagHelperRunner
    -1.06
    ^(@)
    -1.05
    DeleteBehavior
    -1.04
    +#+#
    -1.03
     auffi
    -1.02
     tartalomajánló
    -1.02
    تقاوى
    -1.02
     ་་
    -1.02
     Efq
    -1.02
    POSITIVE LOGITS
     
    0.93
     the
    0.59
     her
    0.54
    2
    0.53
    !
    0.52
    ↵↵
    0.52
    <strong>
    0.52
    3
    0.52
     as
    0.51
     los
    0.51
    Activations Density 0.405%

    No Known Activations