INDEX

Explanations

words indicative of lists, like counting, options, and choices.

oai_token-act-pair · gemini-2.0-flash

present

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

setVerticalGroup

-0.66

RTEX

-0.56

IsMutable

-0.56

AnchorTagHelper

-0.53

ardless

-0.52

buttonBar

-0.51

 nahilalakip

-0.51

 normalcy

-0.51

 indietro

-0.51

}}/>

-0.49

POSITIVE LOGITS



0.68

extAlignment

0.63

 fortnight

0.60

 utafitiHapana

0.60

 AttributeSet

0.59

 arrivant

0.57

 firstly

0.57

Firstly

0.57

 Whilst

0.57

 whilst

0.57

Activations Density 4.404%

words indicative of lists, like counting, options, and choices.

present

No Comments

No Known Activations