INDEX

Explanations

code snippets of website styling and markup

oai_token-act-pair · gemini-2.0-flash

row

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

rug

-0.41

AsUp

-0.40

li

-0.40

putAll

-0.39

ゼン

-0.39

****

-0.38

casila

-0.37

runApp

-0.37

م

-0.36

евна

-0.36

POSITIVE LOGITS

 Majefty

0.92

 purpoſe

0.88

 pleaſure

0.86

 reaſon

0.82

 itſelf

0.81

 greateſt

0.79

 مشين

0.76

 ſche

0.75

 ſta

0.73

 ſeveral

0.73

Activations Density 0.569%

code snippets of website styling and markup

row

No Comments

No Known Activations