INDEX

Explanations

words and phrases that are either positive or negative about food, experiences, and things

oai_token-act-pair · gemini-2.0-flash

about

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

DockStyle

-0.81

ValueStyle

-0.81

findpost

-0.73

bootstrapcdn

-0.68

 OMITBAD

-0.64

ReusableCell

-0.63

ScopeManager

-0.61

 Wiktionnaire

-0.60

wnież

-0.60

úgó

-0.59

POSITIVE LOGITS

closeConnection

0.48

UnusedPrivate

0.45

ffine

0.45

chaub

0.44

ناك

0.43

methe

0.43

انتهای

0.43

 karbon

0.43

low

0.42

CHUNK

0.42

Activations Density 2.622%

words and phrases that are either positive or negative about food, experiences, and things

about

No Comments

No Known Activations