INDEX

Explanations

descriptions of people and things that can be seen

oai_token-act-pair · gemini-2.0-flash

related to seeing

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

 nahilalakip

-1.01

OGND

-0.89

GEBURTSDATUM

-0.88

Rhestr

-0.80

发表于

-0.79

出版年

-0.79

 Administrativna

-0.77

évaluateur

-0.74

#+#

-0.73

 AspNetCore

-0.71

POSITIVE LOGITS

 seen

1.80

seen

1.41

 Seen

1.38

 SEEN

1.33

Seen

1.25

 visible

1.22

 heard

1.22

see

1.06

可见

1.04

 observed

1.01

Activations Density 1.622%

descriptions of people and things that can be seen

related to seeing

No Comments

No Known Activations

descriptions of people and things that can be seen

related to seeing

No Comments

No Known Activations