INDEX

Explanations

words or phrases related to spatial relationships, geometry and orientations.

oai_token-act-pair · gemini-2.0-flash

space

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

__).

-0.48

 numberWith

-0.47

 ffilmiau

-0.42

 concentration

-0.41

หมือน

-0.41

ことなく

-0.41

oxone

-0.41

يكب

-0.40

concentration

-0.40

帯

-0.40

POSITIVE LOGITS

 space

0.97

space

0.89

espace

0.86

 espacio

0.83

 spazio

0.81

 espaço

0.79

Space

0.79

 spaces

0.78

 ruang

0.78

 espace

0.77

Activations Density 1.390%

words or phrases related to spatial relationships, geometry and orientations.

space

No Comments

No Known Activations