INDEX

Explanations

sentences with personal pronouns and auxiliary verbs like "can", "will", or "'t"

oai_token-act-pair · gemini-2.0-flash

t

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

 مشين

-1.11

Efq

-0.84

berdayakan

-0.83

oa̍t

-0.83

 Diſ

-0.81

tonode

-0.81

 Monfieur

-0.77

CPtr

-0.77

 pleaſure

-0.77

 greateſt

-0.76

POSITIVE LOGITS

通

0.50

ath

0.44

es

0.41

des

0.40

 notice

0.39

 Notice

0.38

 ко

0.38

du

0.37

Val

0.37

sp

0.37

Activations Density 1.387%

sentences with personal pronouns and auxiliary verbs like "can", "will", or "'t"

t

No Comments

No Known Activations