© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4881
    Prev
    Next
    INDEX
    Explanations

    sentences expressing a negative or critical opinion

    oai_token-act-pair · gemini-2.0-flash

    negative experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    +:+
    -0.72
    +#+#
    -0.65
     favourably
    -0.62
    IVEREF
    -0.61
    Erstellt
    -0.60
    LookAnd
    -0.59
    dAtA
    -0.59
    . 
    -0.58
     insuffisamment
    -0.58
    );?>
    -0.58
    POSITIVE LOGITS
    EndContext
    0.49
    afficheront
    0.47
     inutile
    0.47
    umab
    0.44
     useless
    0.43
     no
    0.43
    idase
    0.41
    IonicModule
    0.41
    quinone
    0.41
    cycline
    0.41
    Activations Density 2.139%

    No Known Activations