© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6095
    Prev
    Next
    INDEX
    Explanations

    negations and discussions of the lack of something

    oai_token-act-pair · gemini-2.0-flash

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ]--;
    -0.97
     myſelf
    -0.79
    ]++;
    -0.71
     RSSSF
    -0.69
     itſelf
    -0.68
     poffible
    -0.66
     purpoſe
    -0.66
     themſelves
    -0.66
     Offisielt
    -0.65
    ,:);
    -0.65
    POSITIVE LOGITS
    FormTagHelper
    0.53
     كومونز
    0.52
    ParallelGroup
    0.50
    tagHelperRunner
    0.50
     صوتيه
    0.49
    jstor
    0.46
     protoimpl
    0.46
    onAttach
    0.45
    Repost
    0.44
    VersionUID
    0.43
    Activations Density 0.499%

    No Known Activations