INDEX

Explanations

proper nouns, especially names of characters

oai_token-act-pair · gemini-2.0-flash

Sonny

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-1.07

 utafitiHapana

-0.91

MigrationBuilder

-0.81

 AssemblyTitle

-0.79

 snippetHide

-0.77

IsContent

-0.76

 doInBackground

-0.75

awtextra

-0.73

 otomatig

-0.70

RenderAtEndOf

-0.69

POSITIVE LOGITS

laga

0.45

 drop

0.44

ρχ

0.43

ʑ

0.41

 Wrestling

0.41

adona

0.41

geschichte

0.38

 drops

0.38

alsey

0.38

QtWidgets

0.38

Activations Density 10.130%

proper nouns, especially names of characters

Sonny

No Comments

No Known Activations