INDEX

Explanations

the word "bottom" and, less often, "top"

oai_token-act-pair · gemini-2.0-flash

bottom

np_max-act · gemini-2.0-flash

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.91

tagext

-0.70

 barbati

-0.69

 oração

-0.67

mę

-0.66

 cardin

-0.66

 justiça

-0.64

 asiatique

-0.63

 dégust

-0.62

 Romains

-0.61

POSITIVE LOGITS

 }}"></

0.70

 setMessage

0.69

TagHelper

0.69

)$}

0.69

])));

0.65

entown

0.65

`;

0.63

 bezeichneter

0.63

 BoxFit

0.63

 виправивши

0.63

Activations Density 3.628%

the word "bottom" and, less often, "top"

bottom

No Comments

No Known Activations