INDEX

Explanations

arbitrary quotation marks, parenthesis, and markdown.

oai_token-act-pair · gemini-2.0-flash

Story excerpts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

‘

-0.57

-0.56

’

-0.54

–

-0.53

-0.52

-0.51

-0.50

POSITIVE LOGITS

 pleaſure

0.81

 itſelf

0.81

 houſe

0.80

 myſelf

0.78

 ſever

0.77

 ſtate

0.75

 purpoſe

0.75

 auffi

0.73

 Majefty

0.73

 habet

0.72

Activations Density 11.071%

arbitrary quotation marks, parenthesis, and markdown.

Story excerpts

No Comments

No Known Activations