INDEX

Explanations

words that indicate a statement is being evaluated, tested or measured

oai_token-act-pair · gemini-2.0-flash

survive

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

Apis

-0.50

 Améli

-0.48

ällor

-0.48

følge

-0.47

 lizenz

-0.47

 mør

-0.47

 neceff

-0.46

charis

-0.45

 poffe

-0.44

følgelig

-0.43

POSITIVE LOGITS

 survive

1.40

 survived

1.37

 withstand

1.36

 survives

1.35

 Survi

1.34

 resist

1.31

 resistance

1.27

 resists

1.25

 resisting

1.24

survi

1.24

Activations Density 1.738%

words that indicate a statement is being evaluated, tested or measured

survive

No Comments

No Known Activations