INDEX

Explanations

the names of photographers and the word "photo"

oai_token-act-pair · gemini-2.0-flash

images

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

rungsseite

-0.75

principalColumn

-0.74

 esternos

-0.73

spesies

-0.70

 utafitiHapana

-0.68

ContentAsync

-0.68

 تانيه

-0.64

Élet

-0.64

OGND

-0.61

Décès

-0.57

POSITIVE LOGITS

 image

0.80

 images

0.75

 Image

0.70

image

0.68

 Images

0.68

IMAGE

0.66

 imagen

0.65

Image

0.61

Images

0.59

images

0.59

Activations Density 1.940%

the names of photographers and the word "photo"

images

No Comments

No Known Activations