INDEX

Explanations

phrases that suggest there is more content to read

oai_token-act-pair · gemini-2.0-flash

Read

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

<bos>

-1.13

djangoproject

-0.82

IntoConstraints

-0.81

 незавершена

-0.78

posedge

-0.75

Datuak

-0.75

 виправивши

-0.74

__).

-0.74

"):

-0.74

省市镇

-0.73

POSITIVE LOGITS

<eos>

0.49

 AttributeSet

0.47

ana

0.45

во

0.41

fäl

0.40

didReceive

0.40

ани

0.39

ye

0.39

0.38

bių

0.37

Activations Density 0.099%

phrases that suggest there is more content to read

Read

No Comments

No Known Activations