INDEX

Explanations

numbered steps or code-like text

oai_token-act-pair · gemini-2.0-flash

digits

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

 مشين

-0.74

adaptiveStyles

-0.69

tagHelperRunner

-0.69

 Normdatei

-0.68

InSection

-0.67

ReusableCell

-0.66

 <=",

-0.66

AndEndTag

-0.63

mybatisplus

-0.63

Pautan

-0.63

POSITIVE LOGITS

 يتيمه

0.57

Stick

0.46

hap

0.46

 Offisielt

0.44

}")

0.43

}.

0.43

ArgsConstructor

0.43

 Stick

0.41

Instead

0.40

ション

0.40

Activations Density 7.123%

numbered steps or code-like text

digits

No Comments

No Known Activations