INDEX

Explanations

mathematical or symbolic notation and references to figures or steps in technical descriptions.

oai_token-act-pair · gemini-2.0-flash

scientific figures/sections

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.85

-0.74

-0.73

-0.72

<eos>

-0.72

-0.71

POSITIVE LOGITS

Efq

1.41

 itſelf

1.39

 ſeveral

1.38

 myſelf

1.38

 houſe

1.37

 purpoſe

1.36

 raiſ

1.34

 Theſe

1.30

 ſche

1.28

ſelf

1.27

Activations Density 9.983%

mathematical or symbolic notation and references to figures or steps in technical descriptions.

scientific figures/sections

No Comments

No Known Activations