INDEX

Explanations

words indicating possibility or speculation

oai_token-act-pair · gemini-2.0-flash

modal verbs

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

 pinulongan

-0.57

 المعيارى

-0.53

 withdrew

-0.53

DECREF

-0.52

oa̍t

-0.51

brainer

-0.51

]<<"

-0.50

 redou

-0.50

ariously

-0.50

لاع

-0.50

POSITIVE LOGITS

 ModelExpression

0.57

findpost

0.56

СЬ

0.50

Bum

0.49

 transfieras

0.49

uxxxx

0.46

jude

0.45

 Anch

0.45

 astra

0.45

liquez

0.45

Activations Density 1.012%

words indicating possibility or speculation

modal verbs

No Comments

No Known Activations