INDEX

Explanations

send

np_max-act-logits · gemini-2.0-flash

various forms of the verb "send" and related words.

oai_token-act-pair · gemini-2.0-flash

words related to sending

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

AndEndTag

-0.70

numerusform

-0.69

</thead>

-0.68

 "..\..\..\

-0.65

HasAnnotation

-0.60

 ['./

-0.58

 envoyer

-0.58

-0.57

 Ceramby

-0.57

@"/

-0.56

POSITIVE LOGITS

itzender

0.53

catch

0.52

 Prey

0.46

sprechend

0.45

VertexArray

0.45

kosi

0.44

 operativos

0.43

جغرافيا

0.43

ylo

0.43

tovní

0.43

Activations Density 2.989%

send

various forms of the verb "send" and related words.

words related to sending

No Comments

No Known Activations