INDEX

Explanations

references to additional information found later in the text

oai_token-act-pair · gemini-2.0-flash

below

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ostavi

-0.58

sur

-0.53

bag

-0.50

'};

-0.50

bag

-0.49

atsch

-0.48

 vuitton

-0.48

>{@

-0.47

"};

-0.46

ed

-0.46

POSITIVE LOGITS

 CreateTagHelper

0.62

 vandens

0.59

 Monfieur

0.57

 defire

0.56

 uſe

0.55

 pleaſure

0.54

 occaf

0.53

 ſche

0.52

 umbro

0.50

 womanhood

0.50

Activations Density 0.167%

references to additional information found later in the text

below

No Comments

No Known Activations